In machine learning, manifold regularization is a technique for using the shape of a dataset to constrain the functions that should be learned on that dataset. In many machine learning problems, the data to be learned do not cover the entire input space. For example, a facial recognition system may not need to classify any possible image, but only the subset of images that contain faces. The technique of manifold learning assumes that the relevant subset of data comes from a manifold, a mathematical structure with useful properties. The technique also assumes that the function to be learned is smooth: data with different labels are not likely to be close together, and so the labeling function should not change quickly in areas where there are likely to be many data points. Because of this assumption, a manifold regularization algorithm can use unlabeled data to inform where the learned function is allowed to change quickly and where it is not, using an extension of the technique of Tikhonov regularization. Manifold regularization algorithms can extend supervised learning algorithms in semi-supervised learning and transductive learning settings, where unlabeled data are available. The technique has been used for applications including medical imaging, geographical imaging, and object recognition. == Manifold regularizer == === Motivation === Manifold regularization is a type of regularization, a family of techniques that reduces overfitting and ensures that a problem is well-posed by penalizing complex solutions. In particular, manifold regularization extends the technique of Tikhonov regularization as applied to Reproducing kernel Hilbert spaces (RKHSs). Under standard Tikhonov regularization on RKHSs, a learning algorithm attempts to learn a function f {\displaystyle f} from among a hypothesis space of functions H {\displaystyle {\mathcal {H}}} . The hypothesis space is an RKHS, meaning that it is associated with a kernel K {\displaystyle K} , and so every candidate function f {\displaystyle f} has a norm ‖ f ‖ K {\displaystyle \left\|f\right\|_{K}} , which represents the complexity of the candidate function in the hypothesis space. When the algorithm considers a candidate function, it takes its norm into account in order to penalize complex functions. Formally, given a set of labeled training data ( x 1 , y 1 ) , … , ( x ℓ , y ℓ ) {\displaystyle (x_{1},y_{1}),\ldots ,(x_{\ell },y_{\ell })} with x i ∈ X , y i ∈ Y {\displaystyle x_{i}\in X,y_{i}\in Y} and a loss function V {\displaystyle V} , a learning algorithm using Tikhonov regularization will attempt to solve the expression arg min f ∈ H 1 ℓ ∑ i = 1 ℓ V ( f ( x i ) , y i ) + γ ‖ f ‖ K 2 {\displaystyle {\underset {f\in {\mathcal {H}}}{\arg \!\min }}{\frac {1}{\ell }}\sum _{i=1}^{\ell }V(f(x_{i}),y_{i})+\gamma \left\|f\right\|_{K}^{2}} where γ {\displaystyle \gamma } is a hyperparameter that controls how much the algorithm will prefer simpler functions over functions that fit the data better. Manifold regularization adds a second regularization term, the intrinsic regularizer, to the ambient regularizer used in standard Tikhonov regularization. Under the manifold assumption in machine learning, the data in question do not come from the entire input space X {\displaystyle X} , but instead from a nonlinear manifold M ⊂ X {\displaystyle M\subset X} . The geometry of this manifold, the intrinsic space, is used to determine the regularization norm. === Laplacian norm === There are many possible choices for the intrinsic regularizer ‖ f ‖ I {\displaystyle \left\|f\right\|_{I}} . Many natural choices involve the gradient on the manifold ∇ M {\displaystyle \nabla _{M}} , which can provide a measure of how smooth a target function is. A smooth function should change slowly where the input data are dense; that is, the gradient ∇ M f ( x ) {\displaystyle \nabla _{M}f(x)} should be small where the marginal probability density P X ( x ) {\displaystyle {\mathcal {P}}_{X}(x)} , the probability density of a randomly drawn data point appearing at x {\displaystyle x} , is large. This gives one appropriate choice for the intrinsic regularizer: ‖ f ‖ I 2 = ∫ x ∈ M ‖ ∇ M f ( x ) ‖ 2 d P X ( x ) {\displaystyle \left\|f\right\|_{I}^{2}=\int _{x\in M}\left\|\nabla _{M}f(x)\right\|^{2}\,d{\mathcal {P}}_{X}(x)} In practice, this norm cannot be computed directly because the marginal distribution P X {\displaystyle {\mathcal {P}}_{X}} is unknown, but it can be estimated from the provided data. === Graph-based approach of the Laplacian norm === When the distances between input points are interpreted as a graph, then the Laplacian matrix of the graph can help to estimate the marginal distribution. Suppose that the input data include ℓ {\displaystyle \ell } labeled examples (pairs of an input x {\displaystyle x} and a label y {\displaystyle y} ) and u {\displaystyle u} unlabeled examples (inputs without associated labels). Define W {\displaystyle W} to be a matrix of edge weights for a graph, where W i j {\displaystyle W_{ij}} is a similarity built from distance measure between the data points x i {\displaystyle x_{i}} and x j {\displaystyle x_{j}} (so that more close implies higher W i j {\displaystyle W_{ij}} ). Define D {\displaystyle D} to be a diagonal matrix with D i i = ∑ j = 1 ℓ + u W i j {\displaystyle D_{ii}=\sum _{j=1}^{\ell +u}W_{ij}} and L {\displaystyle L} to be the Laplacian matrix D − W {\displaystyle D-W} . Then, as the number of data points ℓ + u {\displaystyle \ell +u} increases, L {\displaystyle L} converges to the Laplace–Beltrami operator Δ M {\displaystyle \Delta _{M}} , which is the divergence of the gradient ∇ M {\displaystyle \nabla _{M}} . Then, if f {\displaystyle \mathbf {f} } is a vector of the values of f {\displaystyle f} at the data, f = [ f ( x 1 ) , … , f ( x l + u ) ] T {\displaystyle \mathbf {f} =[f(x_{1}),\ldots ,f(x_{l+u})]^{\mathrm {T} }} , the intrinsic norm can be estimated: ‖ f ‖ I 2 = 1 ( ℓ + u ) 2 f T L f {\displaystyle \left\|f\right\|_{I}^{2}={\frac {1}{(\ell +u)^{2}}}\mathbf {f} ^{\mathrm {T} }L\mathbf {f} } As the number of data points ℓ + u {\displaystyle \ell +u} increases, this empirical definition of ‖ f ‖ I 2 {\displaystyle \left\|f\right\|_{I}^{2}} converges to the definition when P X {\displaystyle {\mathcal {P}}_{X}} is known. === Solving the regularization problem with graph-based approach === Using the weights γ A {\displaystyle \gamma _{A}} and γ I {\displaystyle \gamma _{I}} for the ambient and intrinsic regularizers, the final expression to be solved becomes: arg min f ∈ H 1 ℓ ∑ i = 1 ℓ V ( f ( x i ) , y i ) + γ A ‖ f ‖ K 2 + γ I ( ℓ + u ) 2 f T L f {\displaystyle {\underset {f\in {\mathcal {H}}}{\arg \!\min }}{\frac {1}{\ell }}\sum _{i=1}^{\ell }V(f(x_{i}),y_{i})+\gamma _{A}\left\|f\right\|_{K}^{2}+{\frac {\gamma _{I}}{(\ell +u)^{2}}}\mathbf {f} ^{\mathrm {T} }L\mathbf {f} } As with other kernel methods, H {\displaystyle {\mathcal {H}}} may be an infinite-dimensional space, so if the regularization expression cannot be solved explicitly, it is impossible to search the entire space for a solution. Instead, a representer theorem shows that under certain conditions on the choice of the norm ‖ f ‖ I {\displaystyle \left\|f\right\|_{I}} , the optimal solution f ∗ {\displaystyle f^{}} must be a linear combination of the kernel centered at each of the input points: for some weights α i {\displaystyle \alpha _{i}} , f ∗ ( x ) = ∑ i = 1 ℓ + u α i K ( x i , x ) {\displaystyle f^{}(x)=\sum _{i=1}^{\ell +u}\alpha _{i}K(x_{i},x)} Using this result, it is possible to search for the optimal solution f ∗ {\displaystyle f^{}} by searching the finite-dimensional space defined by the possible choices of α i {\displaystyle \alpha _{i}} . === Functional approach of the Laplacian norm === The idea beyond the graph-Laplacian is to use neighbors to estimate the Laplacian. This method is akin to local averaging methods, that are known to scale poorly in high-dimensional problems. Indeed, the graph Laplacian is known to suffer from the curse of dimensionality. Luckily, it is possible to leverage expected smoothness of the function to estimate thanks to more advanced functional analysis. This method consists of estimating the Laplacian operator using derivatives of the kernel reading ∂ 1 , j K ( x i , x ) {\displaystyle \partial _{1,j}K(x_{i},x)} where ∂ 1 , j {\displaystyle \partial _{1,j}} denotes the partial derivatives according to the j-th coordinate of the first variable. This second approach to the Laplacian norm is to put in relation with meshfree methods, that contrast with the finite difference method in PDE. == Applications == Manifold regularization can extend a variety of algorithms that can be expressed using Tikhonov regularization, by choosing an appropriate loss function V {\displaystyle V} and hypothesis space H {\displaystyle {\mathcal {H}}} . Two commonly used examples are the families of support vector machines and regularized least squares algorithm
Data remanence
Data remanence is the residual representation of digital data that remains even after attempts have been made to remove or erase the data. This residue may result from data being left intact by a nominal file deletion operation, by reformatting of storage media that does not remove data previously written to the media, or through physical properties of the storage media that allow previously written data to be recovered. Data remanence may make inadvertent disclosure of sensitive information possible should the storage media be released into an uncontrolled environment (e.g., thrown in refuse containers or lost). Various techniques have been developed to counter data remanence. These techniques are classified as clearing, purging/sanitizing, or destruction. Specific methods include overwriting, degaussing, encryption, and media destruction. Effective application of countermeasures can be complicated by several factors, including media that are inaccessible, media that cannot effectively be erased, advanced storage systems that maintain histories of data throughout the data's life cycle, and persistence of data in memory that is typically considered volatile. Several standards exist for the secure removal of data and the elimination of data remanence. == Causes == Many operating systems, file managers, and other software provide a facility where a file is not immediately deleted when the user requests that action. Instead, the file is moved to a holding area (i.e. the "trash"), making it easy for the user to undo a mistake. Similarly, many software products automatically create backup copies of files that are being edited, to allow the user to restore the original version, or to recover from a possible crash (autosave feature). Even when an explicit deleted file retention facility is not provided or when the user does not use it, operating systems do not actually remove the contents of a file when it is deleted unless they are aware that explicit erasure commands are required, like on a solid-state drive. (In such cases, the operating system will issue the Serial ATA TRIM command or the SCSI UNMAP command to let the drive know to no longer maintain the deleted data.) Instead, they simply remove the file's entry from the file system directory because this requires less work and is therefore faster, and the contents of the file—the actual data—remain on the storage medium. The data will remain there until the operating system reuses the space for new data. In some systems, enough filesystem metadata are also left behind to enable easy undeletion by commonly available utility software. Even when undelete has become impossible, the data, until it has been overwritten, can be read by software that reads disk sectors directly. Computer forensics often employs such software. Likewise, reformatting, repartitioning, or reimaging a system is unlikely to write to every area of the disk, though all will cause the disk to appear empty or, in the case of reimaging, empty except for the files present in the image, to most software. Finally, even when the storage media is overwritten, physical properties of the media may permit recovery of the previous contents. In most cases however, this recovery is not possible by just reading from the storage device in the usual way, but requires using laboratory techniques such as disassembling the device and directly accessing/reading from its components. § Complications below gives further explanations for causes of data remanence. == Countermeasures == There are three levels commonly recognized for eliminating remnant data: === Clearing === Clearing is the removal of sensitive data from storage devices in such a way that there is assurance that the data may not be reconstructed using normal system functions or software file/data recovery utilities. The data may still be recoverable, but not without special laboratory techniques. Clearing is typically an administrative protection against accidental disclosure within an organization. For example, before a hard drive is re-used within an organization, its contents may be cleared to prevent their accidental disclosure to the next user. === Purging === Purging or sanitizing is the physical rewrite of sensitive data from a system or storage device done with the specific intent of rendering the data unrecoverable at a later time. Purging, proportional to the sensitivity of the data, is generally done before releasing media beyond control, such as before discarding old media, or moving media to a computer with different security requirements. === Destruction === The storage media is made unusable for conventional equipment. Effectiveness of destroying the media varies by medium and method. Depending on recording density of the media, and/or the destruction technique, this may leave data recoverable by laboratory methods. Conversely, destruction using appropriate techniques is the most secure method of preventing retrieval. == Specific methods == === Overwriting === A common method used to counter data remanence is to overwrite the storage media with new data. This is often called wiping or shredding a disk or file, by analogy to common methods of destroying print media, although the mechanism bears no similarity to these. Because such a method can often be implemented in software alone, and may be able to selectively target only part of the media, it is a popular, low-cost option for some applications. Overwriting is generally an acceptable method of clearing, as long as the media is writable and not damaged. The simplest overwrite technique writes the same data everywhere—often just a pattern of all zeros. At a minimum, this will prevent the data from being retrieved simply by reading from the media again using standard system functions. The UEFI in modern machines may offer an ATA class disk erase function as well. The ATA-6 standard governs secure erases specifications. Bitlocker is whole disk encryption and illegible without the key. Writing a fresh GPT allows a new file system to be established. Blocks will set empty but LBA read is illegible. New data will be unaffected and work fine. In an attempt to counter more advanced data recovery techniques, specific overwrite patterns and multiple passes have often been prescribed. These may be generic patterns intended to eradicate any trace signatures; an example is the seven-pass pattern 0xF6, 0x00, 0xFF,
JAX (software)
JAX is a Python library for accelerator-oriented array computation and program transformation, designed for high-performance numerical computing and large-scale machine learning. It is developed by Google with contributions from Nvidia and other community contributors. It is described as bringing together a modified version of the automatic differentiation system autograd and OpenXLA's XLA (Accelerated Linear Algebra). It is designed to follow the structure and workflow of NumPy as closely as possible and works with various existing frameworks such as TensorFlow and PyTorch. The primary features of JAX are: Providing a unified NumPy-like interface to computations that run on CPU, GPU, or TPU, in local or distributed settings. Built-in Just-In-Time (JIT) compilation via OpenXLA, an open-source machine learning compiler ecosystem. Efficient evaluation of gradients via its automatic differentiation transformations. Automatic vectorization to efficiently map functions over arrays representing batches of inputs. == Libraries using Jax == Flax Equinox Optax
Self-supervised learning
Self-supervised learning (SSL) is a paradigm in machine learning where a model is trained on a task using the data itself to generate supervisory signals, rather than relying on externally-provided labels. In the context of neural networks, self-supervised learning aims to leverage inherent structures or relationships within the input data to create meaningful training signals. SSL tasks are designed so that solving them requires capturing essential features or relationships in the data. The input data is typically augmented or transformed in a way that creates pairs of related samples, where one sample serves as the input, and the other is used to formulate the supervisory signal. This augmentation can involve introducing noise, cropping, rotation, or other transformations. Self-supervised learning more closely imitates the way humans learn to classify objects. During SSL, the model learns in two steps. First, the task is solved based on an auxiliary or pretext classification task using pseudo-labels, which help to initialize the model parameters. Next, the actual task is performed with supervised or unsupervised learning. Self-supervised learning has produced promising results in recent years, and has found practical application in fields such as audio processing, and is being used by Facebook and others for speech recognition. == Pseudo-labels == Pseudo-labels are automatically generated labels that a model assigns to unlabeled data based on its own predictions. They are widely used in self-supervised and semi-supervised learning, where ground-truth annotations are limited or unavailable. By treating predicted labels as surrogate ground truth, learning algorithms can make use of large quantities of unlabeled data in the training process. Pseudo-labeling also plays an important role in systems that must adapt to concept drift, where the statistical properties of the data change over time. In these scenarios, the model may detect that an incoming instance deviates from previously learned behavior. The system then generates a classification result for that instance, and this predicted class is used as a pseudo-label for updating or retraining model components that are becoming outdated. This approach enables continuous adaptation in dynamic environments without requiring manual annotation. In many adaptive learning pipelines, pseudo-labels are chosen when the classifier produces sufficiently confident predictions, reducing the risk of propagating errors. These pseudo-labeled instances are then incorporated into training to refresh or evolve the model's understanding of emerging data patterns, particularly when existing components show signs of “aging” due to drift or distributional shifts. This strategy reduces reliance on manual labeling while helping maintain long-term model performance. == Types == === Autoassociative self-supervised learning === Autoassociative self-supervised learning is a specific category of self-supervised learning where a neural network is trained to reproduce or reconstruct its own input data. In other words, the model is tasked with learning a representation of the data that captures its essential features or structure, allowing it to regenerate the original input. The term "autoassociative" comes from the fact that the model is essentially associating the input data with itself. This is often achieved using autoencoders, which are a type of neural network architecture used for representation learning. Autoencoders consist of an encoder network that maps the input data to a lower-dimensional representation (latent space), and a decoder network that reconstructs the input from this representation. The training process involves presenting the model with input data and requiring it to reconstruct the same data as closely as possible. The loss function used during training typically penalizes the difference between the original input and the reconstructed output (e.g. mean squared error). By minimizing this reconstruction error, the autoencoder learns a meaningful representation of the data in its latent space. === Contrastive self-supervised learning === For a binary classification task, training data can be divided into positive examples and negative examples. Positive examples are those that match the target. For example, if training a classifier to identify birds, the positive training data would include images that contain birds. Negative examples would be images that do not. Contrastive self-supervised learning uses both positive and negative examples. The loss function in contrastive learning is used to minimize the distance between positive sample pairs, while maximizing the distance between negative sample pairs. An early example uses a pair of 1-dimensional convolutional neural networks to process a pair of images and maximize their agreement. Contrastive Language-Image Pre-training (CLIP) allows joint pretraining of a text encoder and an image encoder, such that a matching image-text pair have image encoding vector and text encoding vector that span a small angle (having a large cosine similarity). InfoNCE (Noise-Contrastive Estimation) is a method to optimize two models jointly, based on Noise Contrastive Estimation (NCE). Given a set X = { x 1 , … x N } {\displaystyle X=\left\{x_{1},\ldots x_{N}\right\}} of N {\displaystyle N} random samples containing one positive sample from p ( x t + k ∣ c t ) {\displaystyle p\left(x_{t+k}\mid c_{t}\right)} and N − 1 {\displaystyle N-1} negative samples from the 'proposal' distribution p ( x t + k ) {\displaystyle p\left(x_{t+k}\right)} , it minimizes the following loss function: L N = − E X [ log f k ( x t + k , c t ) ∑ x j ∈ X f k ( x j , c t ) ] {\displaystyle {\mathcal {L}}_{\mathrm {N} }=-\mathbb {E} _{X}\left[\log {\frac {f_{k}\left(x_{t+k},c_{t}\right)}{\sum _{x_{j}\in X}f_{k}\left(x_{j},c_{t}\right)}}\right]} === Non-contrastive self-supervised learning === Non-contrastive self-supervised learning (NCSSL) uses only positive examples. Counterintuitively, NCSSL converges on a useful local minimum rather than reaching a trivial solution, with zero loss. For the example of binary classification, it would trivially learn to classify each example as positive. Effective NCSSL requires an extra predictor on the online side that does not back-propagate on the target side. === Joint-Embedding and Predictive Architectures === A major class of self-supervised learning moves beyond contrastive pairs, instead maximizing the agreement between views while preventing collapse through statistical constraints. Rooted in Deep Canonical Correlation Analysis (Deep CCA), this approach includes Joint-Embedding Architectures (JEA) like Barlow Twins and VICReg, which enforce covariance constraints to learn invariant representations without negative sampling. Deep Latent Variable Path Modelling (DLVPM) generalizes this to multimodal systems, using path models to enforce correlation and orthogonality across diverse data types. In 2022 Yann LeCun introduced Joint-Embedding Predictive Architectures (JEPA) as a step towards decision making, reasoning, and autonomous human intelligence in machines, including self-improvement through autonomous learning. Founded in representation learning, LeCun included the concept of a “world model” in JEPA which aims to enable machines to replicate human intellect by providing machines with a concept for the world in which they exist. Unlike autoencoders, JEPAs operate entirely in latent space, avoiding pixel-level noise to focus on semantic structure. Rather than just learning invariance, JEPAs learn by predicting masked latent representations from visible context. JEPA has been applied to domains such as image analysis, audio processing, and motion in images and video. == Comparison with other forms of machine learning == SSL belongs to supervised learning methods insofar as the goal is to generate a classified output from the input. At the same time, however, it does not require the explicit use of labeled input-output pairs. Instead, correlations, metadata embedded in the data, or domain knowledge present in the input are implicitly and autonomously extracted from the data. These supervisory signals, extracted from the data, can then be used for training. SSL is similar to unsupervised learning in that it does not require labels in the sample data. Unlike unsupervised learning, however, learning is not done using inherent data structures. Semi-supervised learning combines supervised and unsupervised learning, requiring only a small portion of the learning data be labeled. In transfer learning, a model designed for one task is reused on a different task. Training an autoencoder intrinsically constitutes a self-supervised process, because the output pattern needs to become an optimal reconstruction of the input pattern itself. However, in current jargon, the term 'self-supervised' often refers to tasks based on a pretext-task training setup
Neural computation
Neural computation is the information processing performed by networks of neurons. Neural computation is affiliated with the philosophical tradition of computationalism, which advances the thesis that neural computation explains cognition. Warren McCulloch and Walter Pitts were the first to propose an account of neural activity as being computational in their seminal 1943 paper "A Logical Calculus of the Ideas Immanent in Nervous Activity." There are three general branches of computationalism, including classicism, connectionism, and computational neuroscience. All three branches agree that cognition is computation, however, they disagree on what sorts of computations constitute cognition. The classicism tradition believes that computation in the brain is digital, analogous to digital computing. Both connectionism and computational neuroscience do not require that the computations that realize cognition are necessarily digital computations. However, the two branches greatly disagree upon which sorts of experimental data should be used to construct explanatory models of cognitive phenomena. Connectionists rely upon behavioral evidence to construct models to explain cognitive phenomena, whereas computational neuroscience leverages neuroanatomical and neurophysiological information to construct mathematical models that explain cognition. When comparing the three main traditions of the computational theory of mind, as well as the different possible forms of computation in the brain, it is helpful to define what we mean by computation in a general sense. Computation is the processing of information, otherwise known as variables or entities, according to a set of rules. A rule in this sense is simply an instruction for executing a manipulation on the current state of the variable, in order to produce a specified output. In other words, a rule dictates which output to produce given a certain input to the computing system. A computing system is a mechanism whose components must be functionally organized to process the information in accordance with the established set of rules. The types of information processed by a computing system determine which type of computations it performs. Traditionally in cognitive science, there have been two proposed types of computation related to neural activity, digital and analog, with the vast majority of theoretical work incorporating a digital understanding of cognition. Computing systems that perform digital computation are functionally organized to execute operations on strings of digits with respect to the type and location of the digit on the string. It has been argued that neural spike train signaling implements some form of digital computation, since neural spikes may be considered as discrete units or digits, like 0 or 1—the neuron either fires an action potential or it does not. Accordingly, neural spike trains could be seen as strings of digits. Alternatively, analog computing systems perform manipulations on non-discrete, irreducibly continuous variables, that is, entities that vary continuously as a function of time. These sorts of operations are characterized by systems of differential equations. Neural computation can be studied by, for example, building models of neural computation. Work on artificial neural networks has been somewhat inspired by knowledge of neural computation.
History of natural language processing
The history of natural language processing describes the advances of natural language processing. There is some overlap with the history of machine translation, the history of speech recognition, and the history of artificial intelligence. == Early history == The history of machine translation dates back to the seventeenth century, when philosophers such as Leibniz and Descartes put forward proposals for codes which would relate words between languages. All of these proposals remained theoretical, and none resulted in the development of an actual machine. The first patents for "translating machines" were applied for in the mid-1930s. One proposal, by Georges Artsrouni, was simply an automatic bilingual dictionary using paper tape. The other proposal, by Peter Troyanskii, a Russian, was more detailed. Troyanskii’s proposal included both the bilingual dictionary and a method for dealing with grammatical roles between languages, based on Esperanto. == Logical period == In 1950, Alan Turing published his famous article "Computing Machinery and Intelligence" which proposed what is now called the Turing test as a criterion of intelligence. This criterion depends on the ability of a computer program to impersonate a human in a real-time written conversation with a human judge, sufficiently well that the judge is unable to distinguish reliably — on the basis of the conversational content alone — between the program and a real human. In 1957, Noam Chomsky’s Syntactic Structures revolutionized Linguistics with 'universal grammar', a rule-based system of syntactic structures. The Georgetown experiment in 1954 involved fully automatic translation of more than sixty Russian sentences into English. The authors claimed that within three or five years, machine translation would be a solved problem. However, real progress was much slower, and after the ALPAC report in 1966, which found that ten years long research had failed to fulfill the expectations, funding for machine translation was dramatically reduced. Little further research in machine translation was conducted until the late 1980s, when the first statistical machine translation systems were developed. Some notably successful NLP systems developed in the 1960s were SHRDLU, a natural language system working in restricted "blocks worlds" with restricted vocabularies. In 1969 Roger Schank introduced the conceptual dependency theory for natural language understanding. This model, partially influenced by the work of Sydney Lamb, was extensively used by Schank's students at Yale University, such as Robert Wilensky, Wendy Lehnert, and Janet Kolodner. In 1970, William A. Woods introduced the augmented transition network (ATN) to represent natural language input. Instead of phrase structure rules ATNs used an equivalent set of finite-state automata that were called recursively. ATNs and their more general format called "generalized ATNs" continued to be used for a number of years. During the 1970s many programmers began to write 'conceptual ontologies', which structured real-world information into computer-understandable data. Examples are MARGIE (Schank, 1975), SAM (Cullingford, 1978), PAM (Wilensky, 1978), TaleSpin (Meehan, 1976), QUALM (Lehnert, 1977), Politics (Carbonell, 1979), and Plot Units (Lehnert 1981). During this time, many chatterbots were written including PARRY, Racter, and Jabberwacky. == Statistical period == Up to the 1980s, most NLP systems were based on complex sets of hand-written rules. Starting in the late 1980s, however, there was a revolution in NLP with the introduction of machine learning algorithms for language processing. This was due both to the steady increase in computational power resulting from Moore's law and the gradual lessening of the dominance of Chomskyan theories of linguistics (e.g. transformational grammar), whose theoretical underpinnings discouraged the sort of corpus linguistics that underlies the machine-learning approach to language processing. Some of the earliest-used machine learning algorithms, such as decision trees, produced systems of hard if-then rules similar to existing hand-written rules. Increasingly, however, research has focused on statistical models, which make soft, probabilistic decisions based on attaching real-valued weights to the features making up the input data. The cache language models upon which many speech recognition systems now rely are examples of such statistical models. Such models are generally more robust when given unfamiliar input, especially input that contains errors (as is very common for real-world data), and produce more reliable results when integrated into a larger system comprising multiple subtasks. === Datasets === The emergence of statistical approaches was aided by both increase in computing power and the availability of large datasets. At that time, large multilingual corpora were starting to emerge. Notably, some were produced by the Parliament of Canada and the European Union as a result of laws calling for the translation of all governmental proceedings into all official languages of the corresponding systems of government. Many of the notable early successes occurred in the field of machine translation. In 1993, the IBM alignment models were used for statistical machine translation. Compared to previous machine translation systems, which were symbolic systems manually coded by computational linguists, these systems were statistical, which allowed them to automatically learn from large textual corpora. Though these systems do not work well in situations where only small corpora is available, so data-efficient methods continue to be an area of research and development. In 2001, a one-billion-word large text corpus, scraped from the Internet, referred to as "very very large" at the time, was used for word disambiguation. To take advantage of large, unlabelled datasets, algorithms were developed for unsupervised and self-supervised learning. Generally, this task is much more difficult than supervised learning, and typically produces less accurate results for a given amount of input data. However, there is an enormous amount of non-annotated data available (including, among other things, the entire content of the World Wide Web), which can often make up for the inferior results. == Neural period == Neural language models were developed in 1990s. In 1990, the Elman network, using a recurrent neural network, encoded each word in a training set as a vector, called a word embedding, and the whole vocabulary as a vector database, allowing it to perform such tasks as sequence-predictions that are beyond the power of a simple multilayer perceptron. A shortcoming of the static embeddings was that they didn't differentiate between multiple meanings of homonyms. Yoshua Bengio developed the first neural probabilistic language model in 2000. Novel algorithms, availability of larger datasets and higher processing power made possible training of larger and larger language models. Attention mechanism was introduced by Bahdanau et al. in 2014. This work laid the foundations for the famous "Attention Is All You Need" paper that introduced the Transformer architecture in 2017. The concept of large language model (LLM) emerged in late 2010s. LLM is a language model trained with self-supervised learning on vast amount of text. Earliest public LLMs had hundreds of millions of parameters, but this number quickly rose to billion and even trillions. In recent years, advancements in deep learning and large language models have significantly enhanced the capabilities of natural language processing, leading to widespread applications in areas such as healthcare, customer service, and content generation. == Software ==
Labeled data
Labeled data is a group of samples that have been tagged with one or more labels. Labeling typically takes a set of unlabeled data and augments each piece of it with informative tags called judgments. For example, a data label might indicate whether a photo contains a horse or a cow, which words were uttered in an audio recording, what type of action is being performed in a video, what the topic of a news article is, what the overall sentiment of a tweet is, or whether a dot in an X-ray is a tumor. Labels can be obtained by having humans make judgments about a given piece of unlabeled data. Labeled data is significantly more expensive to obtain than the raw unlabeled data. The quality of labeled data directly influences the performance of supervised machine learning models in operation, as these models learn from the provided labels. == Crowdsourced labeled data == In 2006, Fei-Fei Li, the co-director of the Stanford Human-Centered AI Institute, initiated research to improve the artificial intelligence models and algorithms for image recognition by significantly enlarging the training data. The researchers downloaded millions of images from the World Wide Web and a team of undergraduates started to apply labels for objects to each image. In 2007, Li outsourced the data labeling work on Amazon Mechanical Turk, an online marketplace for digital piece work. The 3.2 million images that were labeled by more than 49,000 workers formed the basis for ImageNet, one of the largest hand-labeled database for outline of object recognition. == Automated data labelling == After obtaining a labeled dataset, machine learning models can be applied to the data so that new unlabeled data can be presented to the model and a likely label can be guessed or predicted for that piece of unlabeled data. == Challenges == === Data-driven bias === Algorithmic decision-making is subject to programmer-driven bias as well as data-driven bias. Training data that relies on bias labeled data will result in prejudices and omissions in a predictive model, despite the machine learning algorithm being legitimate. The labeled data used to train a specific machine learning algorithm needs to be a statistically representative sample to not bias the results. For example, in facial recognition systems underrepresented groups are subsequently often misclassified if the labeled data available to train has not been representative of the population,. In 2018, a study by Joy Buolamwini and Timnit Gebru demonstrated that two facial analysis datasets that have been used to train facial recognition algorithms, IJB-A and Adience, are composed of 79.6% and 86.2% lighter skinned humans respectively. === Human error and inconsistency === Human annotators are prone to errors and biases when labeling data. This can lead to inconsistent labels and affect the quality of the data set. The inconsistency can affect the machine learning model's ability to generalize well. === Domain expertise === Certain fields, such as legal document analysis or medical imaging, require annotators with specialized domain knowledge. Without the expertise, the annotations or labeled data may be inaccurate, negatively impacting the machine learning model's performance in a real-world scenario.