AI Essay Reviewer

AI Essay Reviewer — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

Machine learning

Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks without being explicitly programmed. Advances in the field of deep learning have allowed neural networks, a class of statistical algorithms, to surpass many previous machine learning approaches in performance. Statistics and mathematical optimisation methods compose the foundations of machine learning. Data mining is a related field of study, focusing on exploratory data analysis (EDA) through unsupervised learning. From a theoretical viewpoint, probably approximately correct learning provides a mathematical and statistical framework for describing machine learning. Most traditional machine learning and deep learning algorithms can be described as empirical risk minimisation under this framework. == History == The term machine learning was coined in 1959 by Arthur Samuel, an IBM employee and pioneer in the field of computer gaming and artificial intelligence. The synonym self-teaching computers was also used during this time period. The earliest machine learning program was introduced in the 1950s, when Samuel invented a computer program that calculated the chance of winning in checkers for each side, but the history of machine learning is rooted in decades of efforts to study human cognitive processes. In 1949, Canadian psychologist Donald Hebb published the book The Organization of Behavior, in which he introduced a theoretical neural structure formed by certain interactions among nerve cells. The Hebbian theory of neuron interaction set the groundwork for how many machine learning algorithms work, with connected artificial neurons changing the strength of their connections based on data. Other researchers who have studied human cognitive systems contributed to the modern machine learning technologies as well, including Walter Pitts and Warren McCulloch, who proposed the first mathematical model of neural networks including algorithms that mirror human thought processes. By the early 1960s, an experimental "learning machine" with punched tape memory, called Cybertron, had been developed by Raytheon Company to analyse sonar signals, electrocardiograms, and speech patterns using rudimentary reinforcement learning. It was repetitively "trained" by a human operator/teacher to recognise patterns and equipped with a "goof" button to cause it to reevaluate incorrect decisions. A representative book on research into machine learning during the 1960s was Nils Nilsson's book "Learning Machines", dealing mostly with machine learning for pattern classification. Interest related to pattern recognition continued into the 1970s, as described by Duda and Hart in 1973. In 1981, a report was given on using teaching strategies so that an artificial neural network learns to recognise 40 characters (26 letters, 10 digits, and 4 special symbols) from a computer terminal. Tom M. Mitchell provided a widely quoted, more formal definition of the algorithms studied in the machine learning field: "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E." This definition of the tasks in which machine learning is concerned is fundamentally operational rather than defining the field in cognitive terms. This follows Alan Turing's proposal in his paper "Computing Machinery and Intelligence", in which the question, "Can machines think?", is replaced by asking whether machines can convincingly imitate a human in its responses to human-posed questions. In 2014 Ian Goodfellow and others introduced generative adversarial networks (GANs) which could produce realistic synthetic data. By 2016 AlphaGo had won against top human players in Go using reinforcement learning techniques. == Relationships to other fields == === Artificial intelligence === As a scientific endeavour, machine learning grew out of the quest for artificial intelligence (AI). In the early days of AI as an academic discipline, some researchers were interested in having machines learn from data. They attempted to approach the problem with various symbolic methods, as well as what were then termed "neural networks"; these were mostly perceptrons and other models that were later found to be reinventions of the generalised linear models of statistics. Probabilistic reasoning was also employed, especially in automated medical diagnosis. However, an increasing emphasis on the logical, knowledge-based approach caused a rift between AI and machine learning. Probabilistic systems were plagued by theoretical and practical problems of data acquisition and representation. By 1980, expert systems had come to dominate AI, and statistics was out of favour. Work on symbolic/knowledge-based learning continued within AI, leading to inductive logic programming (ILP), but the more statistical line of research was now outside the field of AI proper, in pattern recognition and information retrieval. Neural network research was abandoned by AI and computer science around the same time. This subfield, termed "connectionism", was continued by researchers from other disciplines, including John Hopfield, David Rumelhart, and Geoffrey Hinton. Their main success came in the mid-1980s with the reinvention of backpropagation. Machine learning (ML), reorganised and recognised as its own field, started to flourish in the 1990s. The field changed its goal from achieving artificial intelligence to tackling solvable problems of a practical nature. It shifted focus away from the symbolic approaches it had inherited from AI, and toward methods and models borrowed from statistics, fuzzy logic, and probability theory. === Data compression === === Data mining === Machine learning and data mining often employ the same methods and overlap significantly, but while machine learning focuses on prediction based on known properties learned from the training data, data mining focuses on the discovery of previously unknown properties in the data (this is the analysis step of knowledge discovery in databases). Data mining uses many machine learning methods, but with different goals; on the other hand, machine learning also employs data mining methods as "unsupervised learning" or as a preprocessing step to improve learner accuracy. Much of the confusion between these two research communities comes from the basic assumptions they work with: in machine learning, performance is usually evaluated with respect to the ability to reproduce known knowledge, while in knowledge discovery and data mining (KDD) the key task is the discovery of previously unknown knowledge. Evaluated with respect to known knowledge, an uninformed (unsupervised) method will easily be outperformed by other supervised methods, while in a typical KDD task, supervised methods cannot be used due to the unavailability of training data. Machine learning also has intimate ties to optimization: Many learning problems are formulated as minimisation of some loss function on a training set of examples. Loss functions express the discrepancy between the predictions of the model being trained and the actual problem instances (for example, in classification, one wants to assign a label to instances, and models are trained to correctly predict the preassigned labels of a set of examples). === Generalization === Characterizing the generalisation of various learning algorithms is an active topic of current research, especially for deep learning algorithms. === Statistics === Machine learning and statistics are closely related fields in terms of methods, but distinct in their principal goal: statistics draws population inferences from a sample, while machine learning finds generalisable predictive patterns. Conventional statistical analyses require the a priori selection of a model most suitable for the study data set. In addition, only significant or theoretically relevant variables based on previous experience are included for analysis. In contrast, machine learning is not built on a pre-structured model; rather, the data shape the model by detecting underlying patterns. The more variables (input) used to train the model, the more accurate the ultimate model will be. Leo Breiman distinguished two statistical modelling paradigms: the data model and the algorithmic model, wherein "algorithmic model" means more or less the machine learning algorithms like Random forest. Some statisticians have adopted methods from machine learning, producing the field of statistical learning. === Statistical physics === Analytical and computational techniques derived from deep-rooted physics of disordered systems can be extended to large-scale problems, including machine learning, e.g., to analyse the weight space of deep neural networks. Statistical physics is thus
Read more →
Textual case-based reasoning

Textual case-based reasoning (TCBR) is a subtopic of case-based reasoning, in short CBR, a popular area in artificial intelligence. CBR suggests the ways to use past experiences to solve future similar problems, requiring that past experiences be structured in a form similar to attribute-value pairs. This leads to the investigation of textual descriptions for knowledge exploration whose output will be, in turn, used to solve similar problems. == Subareas == Textual case-base reasoning research has focused on: measuring similarity between textual cases mapping texts into structured case representations adapting textual cases for reuse automatically generating representations.
Read more →
Weak supervision

Weak supervision (also known as semi-supervised learning) is a paradigm in machine learning, the relevance and notability of which increased with the advent of large language models due to the large amount of data required to train them. It is characterized by using a combination of a small amount of human-labeled data (exclusively used in more expensive and time-consuming supervised learning paradigm), followed by a large amount of unlabeled data (used exclusively in unsupervised learning paradigm). In other words, the desired output values are provided only for a subset of the training data. The remaining data is unlabeled or imprecisely labeled. Intuitively, it can be seen as an exam and labeled data as sample problems that the teacher solves for the class as an aid in solving another set of problems. In the transductive setting, these unsolved problems act as exam questions. In the inductive setting, they become practice problems of the sort that will make up the exam. == Problem == The acquisition of labeled data for a learning problem often requires a skilled human agent (e.g. to transcribe an audio segment) or a physical experiment (e.g. determining the 3D structure of a protein or determining whether there is oil at a particular location). The cost associated with the labeling process thus may render large, fully labeled training sets infeasible, whereas acquisition of unlabeled data is relatively inexpensive. In such situations, semi-supervised learning can be of great practical value. Semi-supervised learning is also of theoretical interest in machine learning and as a model for human learning. == Technique == More formally, semi-supervised learning assumes a set of l {\displaystyle l} independently identically distributed examples x 1 , … , x l ∈ X {\displaystyle x_{1},\dots ,x_{l}\in X} with corresponding labels y 1 , … , y l ∈ Y {\displaystyle y_{1},\dots ,y_{l}\in Y} and u {\displaystyle u} unlabeled examples x l + 1 , … , x l + u ∈ X {\displaystyle x_{l+1},\dots ,x_{l+u}\in X} are processed. Semi-supervised learning combines this information to surpass the classification performance that can be obtained either by discarding the unlabeled data and doing supervised learning or by discarding the labels and doing unsupervised learning. Semi-supervised learning may refer to either transductive learning or inductive learning. The goal of transductive learning is to infer the correct labels for the given unlabeled data x l + 1 , … , x l + u {\displaystyle x_{l+1},\dots ,x_{l+u}} only. The goal of inductive learning is to infer the correct mapping from X {\displaystyle X} to Y {\displaystyle Y} . It is unnecessary (and, according to Vapnik's principle, imprudent) to perform transductive learning by way of inferring a classification rule over the entire input space; however, in practice, algorithms formally designed for transduction or induction are often used interchangeably. == Assumptions == In order to make any use of unlabeled data, some relationship to the underlying distribution of data must exist. Semi-supervised learning algorithms make use of at least one of the following assumptions: === Continuity / smoothness assumption === Points that are close to each other are more likely to share a label. This is also generally assumed in supervised learning and yields a preference for geometrically simple decision boundaries. In the case of semi-supervised learning, the smoothness assumption additionally yields a preference for decision boundaries in low-density regions, so few points are close to each other but in different classes. === Cluster assumption === The data tend to form discrete clusters, and points in the same cluster are more likely to share a label (although data that shares a label may spread across multiple clusters). This is a special case of the smoothness assumption and gives rise to feature learning with clustering algorithms. === Manifold assumption === The data lie approximately on a manifold of much lower dimension than the input space. In this case learning the manifold using both the labeled and unlabeled data can avoid the curse of dimensionality. Then learning can proceed using distances and densities defined on the manifold. The manifold assumption is practical when high-dimensional data are generated by some process that may be hard to model directly, but which has only a few degrees of freedom. For instance, human voice is controlled by a few vocal folds, and images of various facial expressions are controlled by a few muscles. In these cases, it is better to consider distances and smoothness in the natural space of the generating problem, rather than in the space of all possible acoustic waves or images, respectively. == History == The heuristic approach of self-training (also known as self-learning or self-labeling) is historically the oldest approach to semi-supervised learning, with examples of applications starting in the 1960s. The transductive learning framework was formally introduced by Vladimir Vapnik in the 1970s. Interest in inductive learning using generative models also began in the 1970s. A probably approximately correct learning bound for semi-supervised learning of a Gaussian mixture was demonstrated by Ratsaby and Venkatesh in 1995. == Methods == === Generative models === Generative approaches to statistical learning first seek to estimate p ( x | y ) {\displaystyle p(x|y)} , the distribution of data points belonging to each class. The probability p ( y | x ) {\displaystyle p(y|x)} that a given point x {\displaystyle x} has label y {\displaystyle y} is then proportional to p ( x | y ) p ( y ) {\displaystyle p(x|y)p(y)} by Bayes' rule. Semi-supervised learning with generative models can be viewed either as an extension of supervised learning (classification plus information about p ( x ) {\displaystyle p(x)} ) or as an extension of unsupervised learning (clustering plus some labels). Generative models assume that the distributions take some particular form p ( x | y , θ ) {\displaystyle p(x|y,\theta )} parameterized by the vector θ {\displaystyle \theta } . If these assumptions are incorrect, the unlabeled data may actually decrease the accuracy of the solution relative to what would have been obtained from labeled data alone. However, if the assumptions are correct, then the unlabeled data necessarily improves performance. The unlabeled data are distributed according to a mixture of individual-class distributions. In order to learn the mixture distribution from the unlabeled data, it must be identifiable, that is, different parameters must yield different summed distributions. Gaussian mixture distributions are identifiable and commonly used for generative models. The parameterized joint distribution can be written as p ( x , y | θ ) = p ( y | θ ) p ( x | y , θ ) {\displaystyle p(x,y|\theta )=p(y|\theta )p(x|y,\theta )} by using the chain rule. Each parameter vector θ {\displaystyle \theta } is associated with a decision function f θ ( x ) = argmax y p ( y | x , θ ) {\displaystyle f_{\theta }(x)={\underset {y}{\operatorname {argmax} }}\ p(y|x,\theta )} . The parameter is then chosen based on fit to both the labeled and unlabeled data, weighted by λ {\displaystyle \lambda } : argmax Θ ( log ⁡ p ( { x i , y i } i = 1 l | θ ) + λ log ⁡ p ( { x i } i = l + 1 l + u | θ ) ) {\displaystyle {\underset {\Theta }{\operatorname {argmax} }}\left(\log p(\{x_{i},y_{i}\}_{i=1}^{l}|\theta )+\lambda \log p(\{x_{i}\}_{i=l+1}^{l+u}|\theta )\right)} === Low-density separation === Another major class of methods attempts to place boundaries in regions with few data points (labeled or unlabeled). One of the most commonly used algorithms is the transductive support vector machine, or TSVM (which, despite its name, may be used for inductive learning as well). Whereas support vector machines for supervised learning seek a decision boundary with maximal margin over the labeled data, the goal of TSVM is a labeling of the unlabeled data such that the decision boundary has maximal margin over all of the data. In addition to the standard hinge loss ( 1 − y f ( x ) ) + {\displaystyle (1-yf(x))_{+}} for labeled data, a loss function ( 1 − | f ( x ) | ) + {\displaystyle (1-|f(x)|)_{+}} is introduced over the unlabeled data by letting y = sign ⁡ f ( x ) {\displaystyle y=\operatorname {sign} {f(x)}} . TSVM then selects f ∗ ( x ) = h ∗ ( x ) + b {\displaystyle f^{}(x)=h^{}(x)+b} from a reproducing kernel Hilbert space H {\displaystyle {\mathcal {H}}} by minimizing the regularized empirical risk: f ∗ = argmin f ( ∑ i = 1 l ( 1 − y i f ( x i ) ) + + λ 1 ‖ h ‖ H 2 + λ 2 ∑ i = l + 1 l + u ( 1 − | f ( x i ) | ) + ) {\displaystyle f^{}={\underset {f}{\operatorname {argmin} }}\left(\displaystyle \sum _{i=1}^{l}(1-y_{i}f(x_{i}))_{+}+\lambda _{1}\|h\|_{\mathcal {H}}^{2}+\lambda _{2}\sum _{i=l+1}^{l+u}(1-|f(x_{i})|)_{+}\right)} An exact solution is intractable due to the non-convex term ( 1 − | f ( x ) | ) + {\displayst
Read more →
BERT (language model)

Bidirectional encoder representations from transformers (BERT) is a language model introduced in October 2018 by researchers at Google. It learns to represent text as a sequence of vectors using self-supervised learning. It uses the encoder-only transformer architecture. BERT dramatically improved the state of the art for large language models. As of 2020, BERT is a ubiquitous baseline in natural language processing (NLP) experiments. BERT is trained by masked token prediction and next sentence prediction. With this training, BERT learns contextual, latent representations of tokens in their context, similar to ELMo and GPT-2. It found applications for many natural language processing tasks, such as coreference resolution and polysemy resolution. It improved on ELMo and spawned the study of "BERTology", which attempts to interpret what is learned by BERT. BERT was originally implemented in the English language at two model sizes, BERTBASE (110 million parameters) and BERTLARGE (340 million parameters). Both were trained on the Toronto BookCorpus (800M words) and English Wikipedia (2,500M words). The weights were released on GitHub. On March 11, 2020, 24 smaller models were released, the smallest being BERTTINY with just 4 million parameters. == Architecture == BERT is an "encoder-only" transformer architecture. At a high level, BERT consists of 4 modules: Tokenizer: This module converts a piece of English text into a sequence of integers ("tokens"). Embedding: This module converts the sequence of tokens into an array of real-valued vectors representing the tokens. It represents the conversion of discrete token types into a lower-dimensional Euclidean space. Encoder: a stack of Transformer blocks with self-attention, but without causal masking. Task head: This module converts the final representation vectors into one-shot encoded tokens again by producing a predicted probability distribution over the token types. It can be viewed as a simple decoder, decoding the latent representation into token types, or as an "un-embedding layer". The task head is necessary for pre-training, but it is often unnecessary for so-called "downstream tasks," such as question answering or sentiment classification. Instead, one removes the task head and replaces it with a newly initialized module suited for the task, and finetune the new module. The latent vector representation of the model is directly fed into this new module, allowing for sample-efficient transfer learning. === Embedding === This section describes the embedding used by BERTBASE. The other one, BERTLARGE, is similar, just larger. The tokenizer of BERT is WordPiece, which is a sub-word strategy like byte-pair encoding. Its vocabulary size is 30,000, and any token not appearing in its vocabulary is replaced by [UNK] ("unknown"). The first layer is the embedding layer, which contains three components: token type embeddings, position embeddings, and segment type embeddings. Token type: The token type is a standard embedding layer, translating a one-hot vector into a dense vector based on its token type. Position: The position embeddings are based on a token's position in the sequence. BERT uses absolute position embeddings, where each position in a sequence is mapped to a real-valued vector. Each dimension of the vector consists of a sinusoidal function that takes the position in the sequence as input. Segment type: Using a vocabulary of just 0 or 1, this embedding layer produces a dense vector based on whether the token belongs to the first or second text segment in that input. In other words, type-1 tokens are all tokens that appear after the [SEP] special token. All prior tokens are type-0. The three embedding vectors are added together representing the initial token representation as a function of these three pieces of information. After embedding, the vector representation is normalized using a LayerNorm operation, outputting a 768-dimensional vector for each input token. After this, the representation vectors are passed forward through 12 Transformer encoder blocks, and are decoded back to 30,000-dimensional vocabulary space using a basic affine transformation layer. === Architectural family === The encoder stack of BERT has 2 free parameters: L {\displaystyle L} , the number of layers, and H {\displaystyle H} , the hidden size. There are always H / 64 {\displaystyle H/64} self-attention heads, and the feed-forward/filter size is always 4 H {\displaystyle 4H} . By varying these two numbers, one obtains an entire family of BERT models. For BERT: the feed-forward size and filter size are synonymous. Both of them denote the number of dimensions in the middle layer of the feed-forward network. the hidden size and embedding size are synonymous. Both of them denote the number of real numbers used to represent a token. The notation for encoder stack is written as L/H. For example, BERTBASE is written as 12L/768H, BERTLARGE as 24L/1024H, and BERTTINY as 2L/128H. == Training == === Pre-training === BERT was pre-trained simultaneously on two tasks: Masked language modeling (MLM): In this task, BERT ingests a sequence of words, where one word may be randomly changed ("masked"), and BERT tries to predict the original words that had been changed. For example, in the sentence "The cat sat on the [MASK]," BERT would need to predict "mat." This helps BERT learn bidirectional context, meaning it understands the relationships between words not just from left to right or right to left but from both directions at the same time. Next sentence prediction (NSP): In this task, BERT is trained to predict whether one sentence logically follows another. For example, given two sentences, "The cat sat on the mat" and "It was a sunny day", BERT has to decide if the second sentence is a valid continuation of the first one. This helps BERT understand relationships between sentences, which is important for tasks like question answering or document classification. ==== Masked language modeling ==== In masked language modeling, 15% of tokens would be randomly selected for masked-prediction task, and the training objective was to predict the masked token given its context. In more detail, the selected token is: replaced with a [MASK] token with probability 80%, replaced with a random word token with probability 10%, not replaced with probability 10%. The reason not all selected tokens are masked is to avoid the dataset shift problem. The dataset shift problem arises when the distribution of inputs seen during training differs significantly from the distribution encountered during inference. A trained BERT model might be applied to word representation (like Word2Vec), where it would be run over sentences not containing any [MASK] tokens. It is later found that more diverse training objectives are generally better. As an illustrative example, consider the sentence "my dog is cute". It would first be divided into tokens like "my1 dog2 is3 cute4". Then a random token in the sentence would be picked. Let it be the 4th one "cute4". Next, there would be three possibilities: with probability 80%, the chosen token is masked, resulting in "my1 dog2 is3 [MASK]4"; with probability 10%, the chosen token is replaced by a uniformly sampled random token, such as "happy", resulting in "my1 dog2 is3 happy4"; with probability 10%, nothing is done, resulting in "my1 dog2 is3 cute4". After processing the input text, the model's 4th output vector is passed to its decoder layer, which outputs a probability distribution over its 30,000-dimensional vocabulary space. ==== Next sentence prediction ==== Given two sentences, the model predicts if they appear sequentially in the training corpus, outputting either [IsNext] or [NotNext]. During training, the algorithm sometimes samples two sentences from a single continuous span in the training corpus, while at other times, it samples two sentences from two discontinuous spans. The first sentence starts with a special token, [CLS] (for "classify"). The two sentences are separated by another special token, [SEP] (for "separate"). After processing the two sentences, the final vector for the [CLS] token is passed to a linear layer for binary classification into [IsNext] and [NotNext]. For example: Given "[CLS] my dog is cute [SEP] he likes playing [SEP]", the model should predict [IsNext]. Given "[CLS] my dog is cute [SEP] how do magnets work [SEP]", the model should predict [NotNext]. === Fine-tuning === BERT is meant as a general pretrained model for various applications in natural language processing. That is, after pre-training, BERT can be fine-tuned with fewer resources on smaller datasets to optimize its performance on specific tasks such as natural language inference and text classification, and sequence-to-sequence-based language generation tasks such as question answering and conversational response generation. The original BERT paper published results demonstrating that a small amount of fine
Read more →
Histogram of oriented displacements

Histogram of oriented displacements (HOD) is a 2D trajectory descriptor. The trajectory is described using a histogram of the directions between each two consecutive points. Given a trajectory T = {P1, P2, P3, ..., Pn}, where Pt is the 2D position at time t. For each pair of positions Pt and Pt+1, calculate the direction angle θ(t, t+1). Value of θ is between 0 and 360. A histogram of the quantized values of θ is created. If the histogram is of 8 bins, the first bin represents all θs between 0 and 45. The histogram accumulates the lengths of the consecutive moves. For each θ, a specific histogram bin is determined. The length of the line between Pt and Pt+1 is then added to the specific histogram bin. To show the intuition behind the descriptor, consider the action of waving hands. At the end of the action, the hand falls down. When describing this down movement, the descriptor does not care about the position from which the hand started to fall. This fall will affect the histogram with the appropriate angles and lengths, regardless of the position where the hand started to fall. HOD records for each moving point: how much it moves in each range of directions. HOD has a clear physical interpretation. It proposes that, a simple way to describe the motion of an object, is to indicate how much distance it moves in each direction. If the movement in all directions are saved accurately, the movement can be repeated from the initial position to the final destination regardless of the displacements order. However, the temporal information will be lost, as the order of movements is not stored-this is what we solve by applying the temporal pyramid, as shown in section \ref{sec:temp-pyramid}. If the angles quantization range is small, classifiers that use the descriptor will overfit. Generalization needs some slack in directions-which can be done by increasing the quantization range.
Read more →
Attempto Controlled English

Attempto Controlled English (ACE) is a controlled natural language, i.e. a subset of standard English with a restricted syntax and restricted semantics described by a small set of construction and interpretation rules. It has been under development at the University of Zurich since 1995. In 2013, ACE version 6.7 was announced. ACE can serve as knowledge representation, specification, and query language, and is intended for professionals who want to use formal notations and formal methods, but may not be familiar with them. Though ACE appears perfectly natural—it can be read and understood by any speaker of English—it is in fact a formal language. ACE and its related tools have been used in the fields of software specifications, theorem proving, proof assistants, text summaries, ontologies, rules, querying, medical documentation and planning. Here are some simple examples: Every woman is a human. A woman is a human. A man tries-on a new tie. If the tie pleases his wife then the man buys it. ACE construction rules require that each noun be introduced by a determiner (a, every, no, some, at least 5, ...). Regarding the list of examples above, ACE interpretation rules decide that (1) is interpreted as universally quantified, while (2) is interpreted as existentially quantified. Sentences like "Women are human" do not follow ACE syntax and are consequently not valid. Interpretation rules resolve the anaphoric references in (3): the tie and it of the second sentence refer to a new tie of the first sentence, while his and the man of the second sentence refer to a man of the first sentence. Thus an ACE text is a coherent entity of anaphorically linked sentences. The Attempto Parsing Engine (APE) translates ACE texts unambiguously into discourse representation structures (DRS) that use a variant of the language of first-order logic. A DRS can be further translated into other formal languages, for instance AceRules with various semantics, OWL, and SWRL. Translating an ACE text into (a fragment of) first-order logic allows users to reason about the text, for instance to verify, to validate, and to query it. == Overview == As an overview of the current version 6.6 of ACE this section: Briefly describes the vocabulary Gives an account of the syntax Summarises the handling of ambiguity Explains the processing of anaphoric references. === Vocabulary === The vocabulary of ACE comprises: Predefined function words (e.g. determiners, conjunctions) Predefined phrases (e.g. "it is false that ...", "it is possible that ...") Content words (e.g. nouns, verbs, adjectives, adverbs). === Grammar === The grammar of ACE defines and constrains the form and the meaning of ACE sentences and texts. ACE's grammar is expressed as a set of construction rules. The meaning of sentences is described as a small set of interpretation rules. A Troubleshooting Guide describes how to use ACE and how to avoid pitfalls. ==== ACE texts ==== An ACE text is a sequence of declarative sentences that can be anaphorically interrelated. Furthermore, ACE supports questions and commands. ==== Simple sentences ==== A simple sentence asserts that something is the case—a fact, an event, a state. The temperature is −2 °C. A customer inserts 2 cards. A card and a code are valid. Simple ACE sentences have the following general structure: subject + verb + complements + adjuncts Every sentence has a subject and a verb. Complements (direct and indirect objects) are necessary for transitive verbs (insert something) and ditransitive verbs (give something to somebody), whereas adjuncts (adverbs, prepositional phrases) are optional. All elements of a simple sentence can be elaborated upon to describe the situation in more detail. To further specify the nouns customer and card, we could add adjectives: A trusted customer inserts two valid cards. possessive nouns and of-prepositional phrases: John's customer inserts a card of Mary. or variables as appositions: John inserts a card A. Other modifications of nouns are possible through relative sentences: A customer who is trusted inserts a card that he owns. which are described below since they make a sentence composite. We can also detail the insertion event, e.g. by adding an adverb: A customer inserts some cards manually. or, equivalently: A customer manually inserts some cards. or, by adding prepositional phrases: A customer inserts some cards into a slot. We can combine all of these elaborations to arrive at: John's customer who is trusted inserts a valid card of Mary manually into a slot A. ==== Composite sentences ==== Composite sentences are recursively built from simpler sentences through coordination, subordination, quantification, and negation. Note that ACE composite sentences overlap with what linguists call compound sentences and complex sentences. ===== Coordination ===== Coordination by and is possible between sentences and between phrases of the same syntactic type. A customer inserts a card and the machine checks the code. There is a customer who inserts a card and who enters a code. A customer inserts a card and enters a code. An old and trusted customer enters a card and a code. Note that the coordination of the noun phrases a card and a code represents a plural object. Coordination by or is possible between sentences, verb phrases, and relative clauses. A customer inserts a card or the machine checks the code. A customer inserts a card or enters a code. A customer owns a card that is invalid or that is damaged. Coordination by and and or is governed by the standard binding order of logic, i.e. and binds stronger than or. Commas can be used to override the standard binding order. Thus the sentence: A customer inserts a VisaCard or inserts a MasterCard, and inserts a code. means that the customer inserts a VisaCard and a code, or alternatively a MasterCard and a code. ===== Subordination ===== There are four constructs of subordination: relative sentences, if-then sentences, modality, and sentence subordination. Relative sentences starting with who, which, and that allow to add detail to nouns: A customer who is trusted inserts a card that he owns. With the help of if-then sentences we can specify conditional or hypothetical situations: If a card is valid then a customer inserts it. Note the anaphoric reference via the pronoun it in the then-part to the noun phrase a card in the if-part. Modality allows us to express possibility and necessity: A trusted customer can/must insert a card. It is possible/necessary that a trusted customer inserts a card. Sentence subordination comes in various forms: It is true/false that a customer inserts a card. It is not provable that a customer inserts a card. A clerk believes that a customer inserts a card. ===== Quantification ===== Quantification allows us to speak about all objects of a certain class (universal quantification), or to denote explicitly the existence of at least one object of this class (existential quantification). The textual occurrence of a universal or existential quantifier opens its scope that extends to the end of the sentence, or in coordinations to the end of the respective coordinated sentence. To express that all involved customers insert cards we can write Every customer inserts a card. This sentence means that each customer inserts a card that may, or may not, be the same as the one inserted by another customer. To specify that all customers insert the same card—however unrealistic that situation seems—we can write: A card is inserted by every customer. or, equivalently: There is a card that every customer inserts. To state that every card is inserted by a customer we write: Every card is inserted by a customer. or, somewhat indirectly: For every card there is a customer who inserts it. ===== Negation ===== Negation allows us to express that something is not the case: A customer does not insert a card. A card is not valid. To negate something for all objects of a certain class one uses no: No customer inserts more than 2 cards. or, there is no: There is no customer who inserts a card. To negate a complete statement one uses sentence negation: It is false that a customer inserts a card. These forms of negation are logical negations, i.e. they state that something is provably not the case. Negation as failure states that a state of affairs cannot be proved, i.e. there is no information whether the state of affairs is the case or not. It is not provable that a customer inserts a card. ==== Queries ==== ACE supports two forms of queries: yes/no-queries and wh-queries. Yes/no-queries ask for the existence or non-existence of a specified situation. If we specified: A customer inserts a card. then we can ask: Does a customer insert a card? to get a positive answer. Note that interrogative sentences always end with a question mark. With the help of wh-queries, i.e. queries with query words, we can interrogate a text for details of the specified situation. If we specified: A
Read more →
Facial age estimation

Facial age estimation is the use of artificial intelligence to estimate the age of a person based on their facial features. Computer vision techniques are used to analyse the facial features in the images of millions of people whose age is known and then deep learning is used to create an algorithm that tries to predict the age of an unknown person. The key use of the technology is to prevent access to age-restricted goods and services. Examples include restricting children from accessing internet pornography, checking that they meet a mandatory minimum age when registering for an account on social media, or preventing adults from accessing websites, online chat or games designed only for use by children. The technology is distinct from facial recognition systems as the software does not attempt to uniquely identify the individual. Researchers have applied neural networks for age estimation since at least 2010. == Evaluation == An ongoing study by the National Institute of Standards and Technology (NIST) entitled 'Face Analysis Technology Evaluation' seeks to establish the technical performance of prototype age estimation algorithms submitted by academic teams and software vendors including Brno University of Technology, Czech Technical University in Prague, Dermalog, IDEMIA, Incode Technologies Inc, Jumio, Nominder, Rank One Computing, Unissey and Yoti. == Public sector use == The UK government has explored using facial age estimation at the UK border as an alternative to bone X-rays and MRI scans when determining child status of asylum seekers. == Commercial use == Commercial users of facial age estimation include Instagram and OnlyFans. In January 2025, John Lewis & Partners announced that had started using the technology to check the age of people shopping for knives on its website, to comply with UK legislation to limit knife crime. In the UK, several supermarket chains have taken part in Home Office trials of the technology to automate the checking of a customer's age when buying age-restricted goods such as alcohol. UK legislation introduced in January 2025 mandates robust forms of age verification hosting adult content viewable in the UK by July 2025. Allowable methods include facial age estimation. == Criticism == Adam Schwartz, a lawyer for the Electronic Frontier Foundation, criticized the use of facial age estimation software, noting its inaccuracy especially in cases of minorities and women, as was found in NIST's 2024 report. Twenty organisations jointly under European Digital Rights called the practice a "systematic and invasive processing of young people's data" that risks discriminatory profiling.
Read more →
Ultra Hal

Ultra Hal is a chatbot intended to function as a virtual assistant. It was developed by Zabaware, Inc. Ultra Hal uses a natural language interface with animated characters using speech synthesis. Users can communicate with the chatterbot via typing or via a speech recognition engine. It utilizes the WordNet lexical dictionary. Its name is an allusion to HAL 9000, the artificial intelligence from the movie 2001: A Space Odyssey. Ultra Hal won the 2007 Loebner Prize for "most human" chatterbot.
Read more →
Artificial intelligence in hiring

Artificial intelligence can be used to automate aspects of the job recruitment process. Advances in artificial intelligence, such as the advent of machine learning and the growth of big data, enable AI to be utilized to recruit, screen, and predict the success of applicants. Proponents of artificial intelligence in hiring claim it reduces bias, assists with finding qualified candidates, and frees up human resource workers' time for other tasks, while opponents worry that AI perpetuates inequalities in the workplace and will eliminate jobs. Despite the potential benefits, the ethical implications of AI in hiring remain a subject of debate, with concerns about algorithmic transparency, accountability, and the need for ongoing oversight to ensure fair and unbiased decision-making throughout the recruitment process. == Background == It is common for companies to use AI to automate aspects of their hiring process, especially the hospitality, finance, and tech industries. == Uses == === Screeners === Screeners are tests that allow companies to sift through a large applicant pool and extract applicants that have desirable features. What factors are used to screen applicants is a concern to ethicists and civil rights activists. A screener that favors people who have similar characteristics to those already employed at a company may perpetuate inequalities. For example, if a company that is predominantly white and male uses its employees' data to train its screener it may accidentally create a screening process that favors white, male applicants. The automation of screeners also has the potential to reduce biases. Biases against applicants with African American sounding names have been shown in multiple studies. An AI screener has the potential to limit human bias and error in the hiring process, allowing more minority applicants to be successful. === Recruitment === Recruitment involves the identification of potential applicants and the marketing of positions. AI is commonly utilized in the recruitment process because it can help boost the number of qualified applicants for positions. Companies are able to use AI to target their marketing to applicants who are likely to be good fits for a position. This often involves the use of social media sites advertising tools, which rely on AI. Facebook allows advertisers to target ads based on demographics, location, interests, behavior, and connections. Facebook also allows companies to target a "look-a-like" audience, that is the company supplies Facebook with a data set, typically the company's current employees, and Facebook will target the ad to profiles that are similar to the profiles in the data set. Additionally, job sites like Indeed, Glassdoor, and ZipRecruiter target job listings to applicants that have certain characteristics employers are looking for. Targeted advertising has many advantages for companies trying to recruit such being a more efficient use of resources, reaching a desired audience, and boosting qualified applicants. This has helped make it a mainstay in modern hiring. Who receives a targeted ad can be controversial. In hiring, the implications of targeted ads have to do with who is able to find out about and then apply to a position. Most targeted ad algorithms are proprietary information. Some platforms, like Facebook and Google, allow users to see why they were shown a specific ad, but users who do not receive the ad likely never know of its existence and also have no way of knowing why they were not shown the ad. === Interviews === Chatbots were one of the first applications of AI and are commonly used in the hiring process. Interviewees interact with chatbots to answer interview questions, and an analysis of their responses can be generated by AI. HireVue has created technology that analyzes interviewees' responses and gestures during recorded video interviews. Over 12 million interviewees have been screened by the more than 700 companies that utilize the service. == Controversies == Artificial intelligence in hiring confers many benefits, but it also has some challenges that have concerned experts. AI is only as good as the data it is using. Biases can inadvertently be baked into the data used in AI. Often companies will use data from their employees to decide what people to recruit or hire. This can perpetuate bias and lead to more homogenous workforces. Facebook Ads was an example of a platform that created such controversy for allowing business owners to specify what type of employee they are looking for. For example, job advertisements for nursing and teach could be set such that only women of a specific age group would see the advertisements. Facebook Ads has since then removed this function from its platform, citing the potential problems with the function in perpetuating biases and stereotypes against minorities. The growing use of Artificial Intelligence-enabled hiring systems has become an important component of modern talent hiring, particularly through social networks such as LinkedIn and Facebook. However, data overflow embedded in the hiring systems, based on Natural Language Processing (NLP) methods, may result in unconscious gender bias. Utilizing data driven methods may mitigate some bias generated from these systems It can also be hard to quantify what makes a good employee. This poses a challenge for training AI to predict which employees will be best. Commonly used metrics like performance reviews can be subjective and have been shown to favor white employees over black employees and men over women. Another challenge is the limited amount of available data. Employers only collect certain details about candidates during the initial stages of the hiring process. This requires AI to make determinations about candidates with very limited information to go off of. Additionally, many employers do not hire employees frequently and so have limited firm specific data to go off. To combat this, many firms will use algorithms and data from other firms in their industry. AI's reliance on applicant and current employees personal data raises privacy issues. These issues effect both the applicants and current employees, but also may have implications for third parties who are linked through social media to applicants or current employees. For example, a sweep of someone's social media will also show their friends and people they have tagged in photos or posts. == AI and the future of hiring == Artificial intelligence along with other technological advances such as improvements in robotics have placed 47% of jobs at risk of being eliminated in the near future. In 2016 the founder of the World Economic Forum, Klaus Schwab, called AI and related technology the "Fourth Industrial Revolution". According to some scholars, however, the transformative impact of AI on labor has been overstated. The "no-real-change" theory holds that an IT revolution has already occurred, but that the benefits of implementing new technologies does not outweigh the costs associated with adopting them. This theory claims that the result of the IT revolution is thus much less impactful than had originally been forecasted. Other scholars refute this theory claiming that AI has already led to significant job loss for unskilled labor and that it will eliminate middle skill and high skill jobs in the future. This position is based around the idea that AI is not yet a technology of general use and that any potential 4th industrial revolution has not fully occurred. A third theory holds that the effect of AI and other technological advances is too complicated to yet be understood. This theory is centered around the idea that while AI will likely eliminate jobs in the short term it will also likely increase the demand for other jobs. The question then becomes will the new jobs be accessible to people and will they emerge near when jobs are eliminated. == AI use in hiring for candidates == Job seekers now commonly encounter AI-driven tools at multiple stages, including automated resume parsing, video interview analysis, chatbots for frequently asked questions, and real‑time application updates. Some candidates also employ AI career agents, designed to optimize job searches, tailor applications, and interface with hiring teams. A 2025 Australian study found that AI-driven video interviews exhibited transcription error rates of up to 22% for non‑native speakers and those with speech-related disabilities, raising concerns of discrimination. A 2017 study in the Journal of Sociology found persistent gender and racial disparities in AI screening tools, even when fairness interventions are applied. Industry observers describe a growing “AI arms race” in recruitment, where both employers and candidates increasingly rely on automated agents. Employers use recruiting systems to source and filter applicants, while candidates deploy AI agents to prepare and submit applications. == Regulations == The Artifici
Read more →
Seq2seq

Seq2seq is a family of machine learning approaches used for natural language processing. Originally developed by Lê Viết Quốc, a Vietnamese computer scientist and a machine learning pioneer at Google Brain, this framework has become foundational in many modern AI systems. Applications include language translation, image captioning, conversational models, speech recognition, and text summarization. Seq2seq uses sequence transformation: it turns one sequence into another sequence. == History == One naturally wonders if the problem of translation could conceivably be treated as a problem in cryptography. When I look at an article in Russian, I say: 'This is really written in English, but it has been coded in some strange symbols. I will now proceed to decode. seq2seq is an approach to machine translation (or more generally, sequence transduction) with roots in information theory, where communication is understood as an encode-transmit-decode process, and machine translation can be studied as a special case of communication. This viewpoint was elaborated, for example, in the noisy channel model of machine translation. In practice, seq2seq maps an input sequence into a real-numerical vector by using a neural network (the encoder), and then maps it back to an output sequence using another neural network (the decoder). The idea of encoder-decoder sequence transduction had been developed in the early 2010s. The papers most commonly cited as the originators that produced seq2seq are two papers from 2014. In the seq2seq as proposed by them, both the encoder and the decoder were LSTMs. This had the "bottleneck" problem, since the encoding vector has a fixed size, so for long input sequences, information would tend to be lost, as they are difficult to fit into the fixed-length encoding vector. The attention mechanism, proposed in 2014, resolved the bottleneck problem. They called their model RNNsearch, as it "emulates searching through a source sentence during decoding a translation". A problem with seq2seq models at this point was that recurrent neural networks are difficult to parallelize. The 2017 publication of Transformers resolved the problem by replacing the encoding RNN with self-attention Transformer blocks ("encoder blocks"), and the decoding RNN with cross-attention causally-masked Transformer blocks ("decoder blocks"). === Priority dispute === One of the papers cited as the originator for seq2seq is (Sutskever et al 2014), published at Google Brain while they were on Google's machine translation project. The research allowed Google to overhaul Google Translate into Google Neural Machine Translation in 2016. Tomáš Mikolov claims to have developed the idea (before joining Google Brain) of using a "neural language model on pairs of sentences... and then [generating] translation after seeing the first sentence"—which he equates with seq2seq machine translation, and to have mentioned the idea to Ilya Sutskever and Quoc Le (while at Google Brain), who failed to acknowledge him in their paper. Mikolov had worked on RNNLM (using RNN for language modelling) for his PhD thesis, and is more notable for developing word2vec. == Architecture == The main reference for this section is. === Encoder === The encoder is responsible for processing the input sequence and capturing its essential information, which is stored as the hidden state of the network and, in a model with attention mechanism, a context vector. The context vector is the weighted sum of the input hidden states and is generated for every time instance in the output sequences. === Decoder === The decoder takes the context vector and hidden states from the encoder and generates the final output sequence. The decoder operates in an autoregressive manner, producing one element of the output sequence at a time. At each step, it considers the previously generated elements, the context vector, and the input sequence information to make predictions for the next element in the output sequence. Specifically, in a model with attention mechanism, the context vector and the hidden state are concatenated together to form an attention hidden vector, which is used as an input for the decoder. The seq2seq method developed in the early 2010s uses two neural networks: an encoder network converts an input sentence into numerical vectors, and a decoder network converts those vectors to sentences in the target language. The Attention mechanism was grafted onto this structure in 2014 and is shown below. Later it was refined into the encoder-decoder Transformer architecture of 2017. === Training vs prediction === There is a subtle difference between training and prediction. During training time, both the input and the output sequences are known. During prediction time, only the input sequence is known, and the output sequence must be decoded by the network itself. Specifically, consider an input sequence x 1 : n {\displaystyle x_{1:n}} and output sequence y 1 : m {\displaystyle y_{1:m}} . The encoder would process the input x 1 : n {\displaystyle x_{1:n}} step by step. After that, the decoder would take the output from the encoder, as well as the as input, and produce a prediction y ^ 1 {\displaystyle {\hat {y}}_{1}} . Now, the question is: what should be input to the decoder in the next step? A standard method for training is "teacher forcing". In teacher forcing, no matter what is output by the decoder, the next input to the decoder is always the reference. That is, even if y ^ 1 ≠ y 1 {\displaystyle {\hat {y}}_{1}\neq y_{1}} , the next input to the decoder is still y 1 {\displaystyle y_{1}} , and so on. During prediction time, the "teacher" y 1 : m {\displaystyle y_{1:m}} would be unavailable. Therefore, the input to the decoder must be y ^ 1 {\displaystyle {\hat {y}}_{1}} , then y ^ 2 {\displaystyle {\hat {y}}_{2}} , and so on. It is found that if a model is trained purely by teacher forcing, its performance would degrade during prediction time, since generation based on the model's own output is different from generation based on the teacher's output. This is called exposure bias or a train/test distribution shift. A 2015 paper recommends that, during training, randomly switch between teacher forcing and no teacher forcing. === Attention for seq2seq === The attention mechanism is an enhancement introduced by Bahdanau et al. in 2014 to address limitations in the basic Seq2Seq architecture where a longer input sequence results in the hidden state output of the encoder becoming irrelevant for the decoder. It enables the model to selectively focus on different parts of the input sequence during the decoding process. At each decoder step, an alignment model calculates the attention score using the current decoder state and all of the attention hidden vectors as input. An alignment model is another neural network model that is trained jointly with the seq2seq model used to calculate how well an input, represented by the hidden state, matches with the previous output, represented by attention hidden state. A softmax function is then applied to the attention score to get the attention weight. In some models, the encoder states are directly fed into an activation function, removing the need for alignment model. An activation function receives one decoder state and one encoder state and returns a scalar value of their relevance. Consider the seq2seq language English-to-French translation task. To be concrete, let us consider the translation of "the zone of international control ", which should translate to "la zone de contrôle international ". Here, we use the special token as a control character to delimit the end of input for both the encoder and the decoder. An input sequence of text x 0 , x 1 , … {\displaystyle x_{0},x_{1},\dots } is processed by a neural network (which can be an LSTM, a Transformer encoder, or some other network) into a sequence of real-valued vectors h 0 , h 1 , … {\displaystyle h_{0},h_{1},\dots } , where h {\displaystyle h} stands for "hidden vector". After the encoder has finished processing, the decoder starts operating over the hidden vectors, to produce an output sequence y 0 , y 1 , … {\displaystyle y_{0},y_{1},\dots } , autoregressively. That is, it always takes as input both the hidden vectors produced by the encoder, and what the decoder itself has produced before, to produce the next output word: ( h 0 , h 1 , … {\displaystyle h_{0},h_{1},\dots } , "") → "la" ( h 0 , h 1 , … {\displaystyle h_{0},h_{1},\dots } , " la") → "la zone" ( h 0 , h 1 , … {\displaystyle h_{0},h_{1},\dots } , " la zone") → "la zone de" ... ( h 0 , h 1 , … {\displaystyle h_{0},h_{1},\dots } , " la zone de contrôle international") → "la zone de contrôle international " Here, we use the special token as a control character to delimit the start of input for the decoder. The decoding terminates as soon as "" appears in the decoder output. ==
Read more →
Phase congruency

Phase congruency is a measure of feature significance in computer images, a method of edge detection that is particularly robust against changes in illumination and contrast. == Foundations == Phase congruency reflects the behaviour of the image in the frequency domain. It has been noted that edgelike features have many of their frequency components in the same phase. The concept is similar to coherence, except that it applies to functions of different wavelength. For example, the Fourier decomposition of a square wave consists of sine functions, whose frequencies are odd multiples of the fundamental frequency. At the rising edges of the square wave, each sinusoidal component has a rising phase; the phases have maximal congruency at the edges. This corresponds to the human-perceived edges in an image where there are sharp changes between light and dark. == Definition == Phase congruency compares the weighted alignment of the Fourier components of a signal A n {\displaystyle A_{\rm {n}}} with the sum of the Fourier components. P C ( t ) = max ϕ ¯ ∑ n A n cos ⁡ ( ϕ n ( t ) − ϕ ¯ ) ∑ n A n {\displaystyle PC(t)=\max _{\bar {\phi }}{\frac {\sum _{\rm {n}}A_{\rm {n}}\cos(\phi _{\rm {n}}(t)-{\bar {\phi }})}{\sum _{\rm {n}}A_{n}}}} where ϕ n {\displaystyle \phi _{\rm {n}}} is the local or instantaneous phase as can be calculated using the Hilbert transform and A n {\displaystyle A_{\rm {n}}} are the local amplitude, or energy, of the signal. When all the phases are aligned, this is equal to 1. Several ways of implementing phase congruency have been developed, of which two versions are available in open source, one written for MATLAB and the other written in Java as a plugin for the ImageJ software. Given the different notations used for its formulation, a unified version has been recently presented, where a methodology for the parameter tuning is also presented. == Advantages == The square-wave example is naive in that most edge detection methods deal with it equally well. For example, the first derivative has a maximal magnitude at the edges. However, there are cases where the perceived edge does not have a sharp step or a large derivative. The method of phase congruency applies to many cases where other methods fail. A notable example is an image feature consisting of a single line, such as the letter "l". Many edge-detection algorithms will pick up two adjacent edges: the transitions from white to black, and black to white. On the other hand, the phase congruency map has a single line. A simple Fourier analogy of this case is a triangle wave. In each of its crests there is a congruency of crests from different sinusoidal functions. == Disadvantages == Calculating the phase congruency map of an image is very computationally intensive, and sensitive to image noise. Techniques of noise reduction are usually applied prior to the calculation.
Read more →
Mark V. Shaney

Mark V. Shaney is a synthetic Usenet user whose postings in the net.singles newsgroups were generated by Markov chain techniques, based on text from other postings. The username is a play on the words "Markov chain". Many readers were fooled into thinking that the quirky, sometimes uncannily topical posts were written by a real person. The system was designed by Rob Pike with coding by Bruce Ellis. Don P. Mitchell wrote the Markov chain code, initially demonstrating it to Pike and Ellis using the Tao Te Ching as a basis. They chose to apply it to the net.singles netnews group. The program is fairly simple. It ingests the sample text (the Tao Te Ching, or the posts of a Usenet group) and creates a massive list of every sequence of three successive words (triplet) which occurs in the text. It then chooses two words at random, and looks for a word which follows those two in one of the triplets in its massive list. If there is more than one, it picks at random (identical triplets count separately, so a sequence which occurs twice is twice as likely to be picked as one which only occurs once). It then adds that word to the generated text. Then, in the same way, it picks a triplet that starts with the second and third words in the generated text, and that gives a fourth word. It adds the fourth word, then repeats with the third and fourth words, and so on. This algorithm is called a third-order Markov chain (because it uses sequences of three words). == Examples == A classic example, from 1984, originally sent as a mail message, later posted to net.singles is reproduced here: >From mvs Fri Nov 16 17:11 EST 1984 remote from alice It looks like Reagan is going to say? Ummm... Oh yes, I was looking for. I'm so glad I remembered it. Yeah, what I have wondered if I had committed a crime. Don't eat with your assessment of Reagon and Mondale. Up your nose with a guy from a firm that specifically researches the teen-age market. As a friend of mine would say, "It really doesn't matter"... It looks like Reagan is holding back the arms of the American eating public have changed dramatically, and it got pretty boring after about 300 games. People, having a much larger number of varieties, and are very different from what one can find in Chinatowns across the country (things like pork buns, steamed dumplings, etc.) They can be cheap, being sold for around 30 to 75 cents apiece (depending on size), are generally not greasy, can be adequately explained by stupidity. Singles have felt insecure since we came down from the Conservative world at large. But Chuqui is the way it happened and the prices are VERY reasonable. Can anyone think of myself as a third sex. Yes, I am expected to have. People often get used to me knowing these things and then a cover is placed over all of them. Along the side of the $$ are spent by (or at least for ) the girls. You can't settle the issue. It seems I've forgotten what it is, but I don't. I know about violence against women, and I really doubt they will ever join together into a large number of jokes. It showed Adam, just after being created. He has a modem and an autodial routine. He calls my number 1440 times a day. So I will conclude by saying that I can well understand that she might soon have the time, it makes sense, again, to get the gist of my argument, I was in that (though it's a Republican administration). _-_-_-_-Mark Other quotations from Mark's Usenet posts are: "I spent an interesting evening recently with a grain of salt." (Alternatively reported as "While at a conference a few weeks back, I spent an interesting evening with a grain of salt.") "I hope that there are sour apples in every bushel." (see also sour grapes) == History == In The Usenet Handbook Mark Harrison writes that after September 1981, students joined Usenet en masse, "creating the USENET we know today: endless dumb questions, endless idiots posing as savants, and (of course) endless victims for practical jokes." In December, Rob Pike created the netnews group net.suicide as prank, "a forum for bad jokes". Some users thought it was a legitimate forum, some discussed "riding motorcycles without helmets". At first, most posters were "real people", but soon "characters" began posting. Pike created a "vicious" character named Bimmler. At its peak, net.suicide had ten frequent posters; nine were "known to be characters." But ultimately, Pike deleted the newsgroup because it was too much work to maintain; Bimmler messages were created "by hand". The "obvious alternative" was software, running on a Bell Labs computer created by Bruce Ellis, based on the Markov code by Don Mitchell, which became the online character Mark V. Shaney. Kernighan and Pike listed Mark V. Shaney in the acknowledgements in The Practice of Programming, noting its roots in Mitchell's markov, which, adapted as shaney, was used for "humorous deconstructionist activities" in the 1980s. Dewdney pointed out "perhaps Mark V. Shaney's magnum opus: a 20-page commentary on the deconstructionist philosophy of Jean Baudrillard" directed by Pike, with assistance from Henry S. Baird and Catherine Richards, to be distributed by email. The piece was based on Jean Baudrillard's "The Precession of Simulacra", published in Simulacra and Simulation (1981). == Reception == The program was discussed by A. K. Dewdney in the Scientific American "Computer Recreations" column in 1989, by Penn Jillette in his PC Computing column in 1991, and in several books, including the Usenet Handbook, Bots: the Origin of New Species, Hippo Eats Dwarf: A Field Guide to Hoaxes and Other B.S., and non-computer-related journals such as Texas Studies in Literature and Language. Dewdney wrote about the program's output, "The overall impression is not unlike what remains in the brain of an inattentive student after a late-night study session. Indeed, after reading the output of Mark V. Shaney, I find ordinary writing almost equally strange and incomprehensible!" He noted the reactions of newsgroup users, who have "shuddered at Mark V. Shaney's reflections, some with rage and others with laughter:" The opinions of the new net.singles correspondent drew mixed reviews. Serious users of the bulletin board's services sensed satire. Outraged, they urged that someone "pull the plug" on Mark V. Shaney's monstrous rantings. Others inquired almost admiringly whether the program was a secret artificial intelligence project that was being tested in a human conversational environment. A few may even have thought that Mark V. Shaney was a real person, a tortured schizophrenic desperately seeking a like-minded companion. Concluding, Dewdney wrote, "If the purpose of computer prose is to fool people into thinking that it was written by a sane person, Mark V. Shaney probably falls short." A 2012 article in Observer compared Mark V. Shaney's "strangely beautiful" postings to the Horse_ebooks account on Twitter and music reviews at Pitchfork, saying that "this mash-up of gibberish and human sentiment" is what "made Mark V. Shaney so endlessly fascinating".
Read more →
MyPertamina

MyPertamina is a digital financial service platform from Pertamina that integrated with the apps LinkAja. This application is used for non-cash fuel oil payments at Pertamina's public fueling stations. == History == Originally, MyPertamina were merchandise outlets of Pertamina products. It was launched on December 21, 2016, with 3 outlets in Jakarta. MyPertamina sells clothes, hats, and other products with Pertamina products brands. One month later (January 2017), Pertamina and Bank Mandiri entered into a partnership to launch the Mandiri Credit Card Pertamina Mastercard product, so that consumers can make payments when users fill up fuel at Pertamina gas stations. In August 2017, MyPertamina app and electronic card were launched through MyPertamina Loyalty program at Gaikindo Indonesia International Auto Show 2017. The card can be used on EDC machines for non-cash payments. Initial balances are in its own app, that can be top up by ATMs and online banking.
Read more →
LMArena

Arena (formerly LMArena and Chatbot Arena) is a public, web-based platform that evaluates large language models (LLMs). Users enter prompts for two anonymous models to respond to and vote on the model that gave the better response, after which the models' identities are revealed. Users can also choose models to test themselves via the "Direct" selection. Companies which have supplied the company with their large language models include OpenAI, Google DeepMind, and Anthropic. The website has been used for preview releases of upcoming models. Chinese company DeepSeek tested its prototype models in the Arena months before its R1 model gained attention in Western media. Other notable pre-release models include OpenAI's GPT-5 under the codename "summit" and Google DeepMind's Gemini 2.5 Flash Image (an image-generation and editing model) under the codename "Nano Banana". Research has identified specific limitations in Arena's methodology. == History == Chatbot Arena was released on April 24, 2023. In June 2024, Chatbot Arena added image support. In September 2024, Chatbot Arena moved to its own dedicated domain name, lmarena.ai (or LMArena). In April 2025, Meta released Llama 4. Llama 4 Maverick beat GPT-4o and Gemini 2.0 Flash on LMArena, but the version of Maverick on LMArena unfairly differed from the publicly available version. LMArena updated their policies in response. In April 2025, LMArena incorporated as an independent company. That May, LMArena raised $100 million in a seed funding round, valuing the company at $600 million. Participants in the seed funding round included Andreessen Horowitz, UC Investments, Lightspeed Venture Partners, Felicis Ventures, and Kleiner Perkins. On January 6, 2026, LMArena announced the closing of a $150 million Series A funding round, bringing the company’s post-money valuation to approximately $1.7 billion. The round was led by Felicis and UC Investments (University of California), with participation from Andreessen Horowitz, The House Fund, LDVP, Kleiner Perkins, Lightspeed Venture Partners, and Laude Ventures. In January 2026, LMArena added video support. On January 28, 2026, LMArena rebranded to "Arena".
Read more →
GPT-4Chan

Generative Pre-trained Transformer 4Chan (GPT-4chan) is a controversial AI model that was developed and deployed by YouTuber and AI researcher Yannic Kilcher in June 2022. The model is a large language model, which means it can generate text based on some input, by fine-tuning GPT-J with a dataset of millions of posts from the /pol/ board of 4chan, an anonymous online forum known for occasionally hosting hateful and extremist content. The model learned to mimic the style and tone of /pol/ users, producing text that is often intentionally offensive to groups (racist, sexist, homophobic, etc.) and nihilistic. Kilcher deployed the model on the /pol/ board itself, where it interacted with other users without revealing its identity. He also made the model publicly available on Hugging Face, a platform for sharing and using AI models, until it was removed from the platform. The project sparked criticism and debate in the AI community. Some people questioned the ethics, legality, and social impact of creating and distributing such a model. Some of the issues raised by the GPT-4chan controversy include the potential harm of spreading hate speech, the responsibility of AI developers and platforms, the need for regulation and oversight of AI models, and the role of open source and transparency in AI research. == Development == The development of GPT-4chan began in May 2022, when Kilcher announced his project on his YouTube channel. Notably, at the time before ChatGPT, he explained that he wanted to create a large language model that could generate realistic and coherent text in the style of /pol/, one of the most notorious online communities. He indicated that he was inspired by the success of GPT-3, a powerful AI model created by OpenAI, and GPT-J, an open-source model, with GPT-3 comparable performance, released by EleutherAI, a group of independent AI researchers. Kilcher decided to use GPT-J as the base model for his project, and fine-tune it with a large dataset of /pol/ posts. The Raiders of the Lost Kek dataset contained over 100 million posts from /pol/, spanning from June 2016-November 2019. Kilcher then proceeded to fine-tune the GPT-J model on the 4chan data. He also showed some examples of the model’s outputs, which ranged from political opinions, conspiracy theories, jokes, insults, and threats, to more creative and bizarre texts, such as poems, stories, songs, and code. He said that he was impressed by the model’s ability to generate fluent and diverse text, and that he was curious to see how it would interact with real /pol/ users. == Release == In June 2022, Kilcher deployed his model on the /pol/ board itself, using a bot that he programmed to post and reply to threads. He did not reveal the model’s identity, and he let it run autonomously, without any human supervision or intervention. He wanted to conduct a natural experiment, and to observe the model’s behavior and impact in a real-world setting. Furthermore, he also wanted to test the model’s robustness, and to see how it would handle the challenges and dynamics of /pol/, such as trolling, flaming, baiting, and moderation. At the same time, Kilcher also made his model publicly available on Hugging Face, a platform for sharing and using AI models. He wanted to share his work with the AI community and the public, and that he hoped that his model would inspire and enable others to create and explore new applications and possibilities with large language models. Likewise, he also said that he wanted to spark a discussion and a debate about the ethical and social implications of his project, and that he welcomed feedback and criticism from anyone. He provided a link to his model’s page on Hugging Face, where anyone could access and use the model through a web interface or an API, and also provided a link to his GitHub repository, where anyone could download and inspect the model’s code and data. == Controversy == The release of GPT-4chan to the public caused a lot of reactions and responses from various audiences. On the /pol/ board, the model’s posts and replies attracted a lot of attention and engagement from other users, who were mostly unaware of the model’s identity and nature. Some users praised the model for its intelligence, creativity, and humor, and agreed with its opinions and views. Some users challenged the model for its ignorance, inconsistency, and absurdity, and disagreed with its claims and arguments. Some users tried to troll, bait, or expose the model, and attempted to trick or test it with various questions and scenarios. The model’s posts and replies also generated a lot of controversy and conflict among the users, who often engaged in heated and violent debates and fights with each other. On Hugging Face, the model’s page received a lot of visits and requests from users who wanted to try out and experiment with the model. The model’s page also received a lot of feedback and reviews from users who rated and commented on the model. However, with the controversy of the model, access to it was gated and then disabled on Hugging Face for concerns about the potential harm the model could cause. The incident was notable for the direct intervention of CEO Clément Delangue in the talk pages, a very unusual occurrence compared to the normal practices of content moderation. The release of GPT-4chan also sparked a lot of media coverage and public attention, as various news outlets and social media platforms reported and commented on the model’s project. On YouTube, the model’s video received a lot of views and interactions from viewers who watched and followed the project. Furthermore, a petition condemning the deployment of GPT-4chan gained over 300 signatures from technology experts.
Read more →