AI Email Client

AI Email Client — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

Big data

Big data primarily refers to data sets that are too large or complex to be dealt with by traditional data-processing software. Data with many entries (rows) offers greater statistical power, while data with higher complexity (more attributes or columns) may lead to a higher false discovery rate. Big data analysis challenges include capturing data, data storage, data analysis, search, sharing, transfer, visualization, querying, updating, information privacy, and data sources. Big data was originally associated with three key concepts: volume, variety, and velocity. The analysis of big data that have only volume, velocity, and variety can pose challenges in sampling. A fourth concept, veracity, which refers to the level of reliability of data, was thus added. Without sufficient investment in expertise to ensure big data veracity, the volume and variety of data can produce costs and risks that exceed an organization's capacity to create and capture value from big data. Current usage of the term big data tends to refer to the use of predictive analytics, user behavior analytics, or certain other advanced data analytics methods that extract value from big data, and seldom to a particular size of data set. "There is little doubt that the quantities of data now available are indeed large, but that's not the most relevant characteristic of this new data ecosystem." Analysis of data sets can find new correlations to "spot business trends, prevent diseases, combat crime and so on". Scientists, business executives, medical practitioners, advertising and governments alike regularly meet difficulties with large datasets in areas including Internet searches, fintech, healthcare analytics, geographic information systems, urban informatics, and business informatics. Scientists encounter limitations in e-Science work, including meteorology, genomics, connectomics, complex physics simulations, biology, and environmental research. The size and number of available data sets have grown rapidly as data is collected by devices such as mobile devices, cheap and numerous information-sensing Internet of things devices, aerial (remote sensing) equipment, software logs, cameras, microphones, radio-frequency identification (RFID) readers and wireless sensor networks. The world's technological per-capita capacity to store information has roughly doubled every 40 months since the 1980s; as of 2012, every day 2.5 exabytes (2.17×260 bytes) of data are generated. Based on an IDC report prediction, the global data volume was predicted to grow exponentially from 4.4 zettabytes to 44 zettabytes between 2013 and 2020. By 2025, IDC predicts there will be 163 zettabytes of data. According to IDC, global spending on big data and business analytics (BDA) solutions is estimated to reach $215.7 billion in 2021. Statista reported that the global big data market is forecasted to grow to $103 billion by 2027. In 2011 McKinsey & Company reported, if US healthcare were to use big data creatively and effectively to drive efficiency and quality, the sector could create more than $300 billion in value every year. In the developed economies of Europe, government administrators could save more than €100 billion ($149 billion) in operational efficiency improvements alone by using big data. And users of services enabled by personal-location data could capture $600 billion in consumer surplus. One question for large enterprises is determining who should own big-data initiatives that affect the entire organization. Relational database management systems and desktop statistical software packages used to visualize data often have difficulty processing and analyzing big data. The processing and analysis of big data may require "massively parallel software running on tens, hundreds, or even thousands of servers". What qualifies as "big data" varies depending on the capabilities of those analyzing it and their tools. Furthermore, expanding capabilities make big data a moving target. "For some organizations, facing hundreds of gigabytes of data for the first time may trigger a need to reconsider data management options. For others, it may take tens or hundreds of terabytes before data size becomes a significant consideration." == Definition == The term big data has been in use since the 1990s, with some giving credit to John Mashey for popularizing the term. Big data usually includes data sets with sizes beyond the ability of commonly used software tools to capture, curate, manage, and process data within a tolerable elapsed time. Big data philosophy encompasses unstructured, semi-structured and structured data; however, the main focus is on unstructured data. Big data "size" is a constantly moving target; as of 2012 ranging from a few dozen terabytes to many zettabytes of data. Big data requires a set of techniques and technologies with new forms of integration to reveal insights from datasets that are diverse, complex, and of a massive scale. Variability is often included as an additional quality of big data. A 2018 definition states "Big data is where parallel computing tools are needed to handle data", and notes, "This represents a distinct and clearly defined change in the computer science used, via parallel programming theories, and losses of some of the guarantees and capabilities made by Codd's relational model." In a comparative study of big datasets, Kitchin and McArdle found that none of the commonly considered characteristics of big data appear consistently across all of the analyzed cases. For this reason, other studies identified the redefinition of power dynamics in knowledge discovery as the defining trait. Instead of focusing on the intrinsic characteristics of big data, this alternative perspective pushes forward a relational understanding of the object claiming that what matters is the way in which data is collected, stored, made available and analyzed. === Big data vs. business intelligence === The growing maturity of the concept more starkly delineates the difference between "big data" and "business intelligence": Business intelligence uses applied mathematics tools and descriptive statistics with data with high information density to measure things, detect trends, etc. Big data uses mathematical analysis, optimization, inductive statistics, and concepts from nonlinear system identification to infer laws (regressions, nonlinear relationships, and causal effects) from large sets of data with low information density to reveal relationships and dependencies, or to perform predictions of outcomes and behaviors. == Characteristics == Big data can be described by the following characteristics: Volume The quantity of generated and stored data. The size of the data determines the value and potential insight, and whether it can be considered big data or not. The size of big data is usually larger than terabytes and petabytes. Variety The type and nature of the data. Earlier technologies like RDBMSs were capable to handle structured data efficiently and effectively. However, the change in type and nature from structured to semi-structured or unstructured challenged the existing tools and technologies. Big data technologies evolved with the prime intention to capture, store, and process the semi-structured and unstructured (variety) data generated with high speed (velocity), and huge in size (volume). Later, these tools and technologies were explored and used for handling structured data also but preferable for storage. Eventually, the processing of structured data was still kept as optional, either using big data or traditional RDBMSs. This helps in analyzing data towards effective usage of the hidden insights exposed from the data collected via social media, log files, sensors, etc. Big data draws from text, images, audio, video; plus it completes missing pieces through data fusion. Velocity The speed at which the data is generated and processed to meet the demands and challenges that lie in the path of growth and development. Big data is often available in real-time. Compared to small data, big data is produced more continually. Two kinds of velocity related to big data are the frequency of generation and the frequency of handling, recording, and publishing. Veracity The truthfulness or reliability of the data, which refers to the data quality and the data value. Big data must not only be large in size, but also must be reliable in order to achieve value in the analysis of it. The data quality of captured data can vary greatly, affecting an accurate analysis. Value The worth in information that can be achieved by the processing and analysis of large datasets. Value also can be measured by an assessment of the other qualities of big data. Value may also represent the profitability of information that is retrieved from the analysis of big data. Variability The characteristic of the changing formats, structure, or sources of big data. Big data can include structured, unstructured,
Read more →
Markov information source

In mathematics, a Markov information source, or simply, a Markov source, is an information source whose underlying dynamics are given by a stationary finite Markov chain. == Formal definition == An information source is a sequence of random variables ranging over a finite alphabet Γ {\displaystyle \Gamma } , having a stationary distribution. A Markov information source is then a (stationary) Markov chain M {\displaystyle M} , together with a function f : S → Γ {\displaystyle f:S\to \Gamma } that maps states S {\displaystyle S} in the Markov chain to letters in the alphabet Γ {\displaystyle \Gamma } . A unifilar Markov source is a Markov source for which the values f ( s k ) {\displaystyle f(s_{k})} are distinct whenever each of the states s k {\displaystyle s_{k}} are reachable, in one step, from a common prior state. Unifilar sources are notable in that many of their properties are far more easily analyzed, as compared to the general case. == Applications == Markov sources are commonly used in communication theory, as a model of a transmitter. Markov sources also occur in natural language processing, where they are used to represent hidden meaning in a text. Given the output of a Markov source, whose underlying Markov chain is unknown, the task of solving for the underlying chain is undertaken by the techniques of hidden Markov models, such as the Viterbi algorithm.
Read more →
Markov information source

In mathematics, a Markov information source, or simply, a Markov source, is an information source whose underlying dynamics are given by a stationary finite Markov chain. == Formal definition == An information source is a sequence of random variables ranging over a finite alphabet Γ {\displaystyle \Gamma } , having a stationary distribution. A Markov information source is then a (stationary) Markov chain M {\displaystyle M} , together with a function f : S → Γ {\displaystyle f:S\to \Gamma } that maps states S {\displaystyle S} in the Markov chain to letters in the alphabet Γ {\displaystyle \Gamma } . A unifilar Markov source is a Markov source for which the values f ( s k ) {\displaystyle f(s_{k})} are distinct whenever each of the states s k {\displaystyle s_{k}} are reachable, in one step, from a common prior state. Unifilar sources are notable in that many of their properties are far more easily analyzed, as compared to the general case. == Applications == Markov sources are commonly used in communication theory, as a model of a transmitter. Markov sources also occur in natural language processing, where they are used to represent hidden meaning in a text. Given the output of a Markov source, whose underlying Markov chain is unknown, the task of solving for the underlying chain is undertaken by the techniques of hidden Markov models, such as the Viterbi algorithm.
Read more →
Generalized nondeterministic finite automaton

In the theory of computation, a generalized nondeterministic finite automaton (GNFA), also known as an expression automaton or a generalized nondeterministic finite state machine, is a variation of a nondeterministic finite automaton (NFA) where each transition is labeled with any regular expression. The GNFA reads blocks of symbols from the input which constitute a string as defined by the regular expression on the transition. There are several differences between a standard finite state machine and a generalized nondeterministic finite state machine. A GNFA must have only one start state and one accept state, and these cannot be the same state, whereas an NFA or DFA both may have several accept states, and the start state can be an accept state. A GNFA must have only one transition between any two states, whereas a NFA or DFA both allow for numerous transitions between states. In a GNFA, a state has a single transition to every state in the machine, although often it is a convention to ignore the transitions that are labelled with the empty set when drawing generalized nondeterministic finite state machines. == Formal definition == A GNFA can be defined as a 5-tuple, (S, Σ, T, s, a), consisting of a finite set of states (S); a finite set called the alphabet (Σ); a transition function (T : (S ∖ {\displaystyle \setminus } {a}) × (S ∖ {\displaystyle \setminus } {s}) → R); a start state (s ∈ S); an accept state (a ∈ S); where R is the collection of all regular expressions over the alphabet Σ. The transition function takes as its argument a pair of two states and outputs a regular expression (the label of the transition). This differs from other finite state machines, which take as input a single state and an input from the alphabet (or the empty string in the case of nondeterministic finite state machines) and outputs the next state (or the set of possible states in the case of nondeterministic finite state machines). A DFA or NFA can easily be converted into a GNFA and then the GNFA can be easily converted into a regular expression by repeatedly collapsing parts of it to single edges until S = {s, a}. Similarly, GNFAs can be reduced to NFAs by changing regular expression operators into new edges until each edge is labelled with a regular expression matching a single string of length at most 1. NFAs, in turn, can be reduced to DFAs using the powerset construction. This shows that GNFAs recognize the same set of formal languages as DFAs and NFAs.
Read more →
DBGallery

DBGallery, short for Database Gallery, is a cloud-based Software as a Service (SaaS) and on-prem webserver for teams of various sizes. DBGallery enables users to centrally store, manage, catalog, archive, and securely share image, video, and document files. It facilitates version control, detects duplicates, and offers an intuitive and advanced search functionality, making assets easily accessible to all users. It takes advantage of current AI technologies to automatically add significant metadata to images, facilitates custom-trained AI models, and offers bespoke AI features. Additionally, DBGallery provides team management tools, workflow management, an activity audit trail, and other collaborative features that foster a productive environment for both internal and external stakeholders. == History == DBGallery's first public release was December 2007. Since then each year has seen continuous enhancements. 2013 added support for additional non-English languages in its meta-data. 2014 added support for creating custom data fields for tagging and search. In 2015 included the ability to auto-tag images using Reverse Geocoding. 2018 added artificial intelligence (AI) image recognition as a further addition to auto-tagging. March 2020 added complete image collection management via the web (e.g. file and folder drag and drop), a new collection dashboard, custom data layouts, and an improved audit trail. 2021 saw user experience improvements provided by improved styling and performance enhancements. Version 12 was released in October 2021. It added the ability to upload unlimited file sizes and made significant performance improvements for very large collections. June 2022 saw the release of a global duplicate images search. In late 2022, DBGallery began offering significantly reduced cloud storage cost, at a third of its previous prices, which played into its recent high-volume/high-capacity capabilities and its clients' subsequent demand for additional storage. 2023 saw improvements in user and role management, introduced it's mobile app (PWA), and improved custom-trained object detection. Release 14.0 in the spring of 2024 had large sharing improvements and a new find related images feature. Winter 2025's v15 release introduced AI-generated image descriptions, image-to-text, and facial recognition.
Read more →
P4-metric

The P4 metric (also known as FS or Symmetric F ) enables performance evaluation of a binary classifier. The P4 metric is calculated from precision, recall, specificity, and NPV (negative predictive value). The definition of the P4 metric is similar to that of the F1 metric, however the P4 metric definition addresses criticisms leveled against the definition of the F1 metric. The definition of the P4 metric may, therefore, be understood as an extension of the F1 metric. Like the other known metrics, the P4 metric is a function of: TP (true positives), TN (true negatives), FP (false positives), FN (false negatives). == Justification == The key concept of the P4 metric is to leverage the four key conditional probabilities: P ( + ∣ C + ) {\displaystyle P(+\mid C{+})} — the probability that the sample is positive, provided the classifier result was positive. P ( C + ∣ + ) {\displaystyle P(C{+}\mid +)} — the probability that the classifier result will be positive, provided the sample is positive. P ( C − ∣ − ) {\displaystyle P(C{-}\mid -)} — the probability that the classifier result will be negative, provided the sample is negative. P ( − ∣ C − ) {\displaystyle P(-\mid C{-})} — the probability the sample is negative, provided the classifier result was negative. The main assumption behind this metric is that all the probabilities mentioned above are close to 1 for a properly designed binary classifier. Indeed, P 4 = 1 {\displaystyle \mathrm {P} _{4}=1} if, and only if, all of the probabilities above are equal to 1. Another important feature is that P 4 {\displaystyle \mathrm {P} _{4}} tends to zero any of the above probabilities tend to zero. == Definition == P4 is defined as a harmonic mean of four key conditional probabilities: P 4 = 4 1 P ( + ∣ C + ) + 1 P ( C + ∣ + ) + 1 P ( C − ∣ − ) + 1 P ( − ∣ C − ) = 4 1 p r e c i s i o n + 1 r e c a l l + 1 s p e c i f i c i t y + 1 N P V . {\displaystyle \mathrm {P} _{4}={\frac {4}{{\frac {1}{P(+\mid C{+})}}+{\frac {1}{P(C{+}\mid +)}}+{\frac {1}{P(C{-}\mid -)}}+{\frac {1}{P(-\mid C{-})}}}}={\frac {4}{{\frac {1}{\mathit {precision}}}+{\frac {1}{\mathit {recall}}}+{\frac {1}{\mathit {specificity}}}+{\frac {1}{\mathit {NPV}}}}}.} In terms of TP,TN,FP,FN it can be calculated as follows: P 4 = 4 ⋅ T P ⋅ T N 4 ⋅ T P ⋅ T N + ( T P + T N ) ⋅ ( F P + F N ) . {\displaystyle \mathrm {P} _{4}={\frac {4\cdot \mathrm {TP} \cdot \mathrm {TN} }{4\cdot \mathrm {TP} \cdot \mathrm {TN} +(\mathrm {TP} +\mathrm {TN} )\cdot (\mathrm {FP} +\mathrm {FN} )}}.} == Evaluation of the binary classifier performance == Evaluating the performance of binary classifiers is a multidisciplinary concept. It spans from the evaluation of medical tests, psychiatric tests to machine learning classifiers from a variety of fields. Thus, many of the metrics in use exist under several names, some defined independently. == Properties of P4 metric == Symmetry — contrasting to the F1 metric, P4 is symmetrical. It means - it does not change its value when dataset labeling is changed - positives named negatives and negatives named positives. Range: P 4 ∈ [ 0 , 1 ] {\displaystyle \mathrm {P} _{4}\in [0,1]} . Achieving P 4 ≈ 1 {\displaystyle \mathrm {P} _{4}\approx 1} requires all the key four conditional probabilities being close to 1. For P 4 ≈ 0 {\displaystyle \mathrm {P} _{4}\approx 0} it is sufficient that one of the key four conditional probabilities is close to 0. == Examples, comparing with the other metrics == Dependency table for selected metrics ("true" means depends, "false" - does not depend): Metrics that do not depend on a given probability are prone to misrepresentation when the probability approaches 0. === Example 1: Rare disease detection test === Let us consider a medical test used to detect a rare disease. Suppose a population size of 100000 and 0.05% of the population is infected. Further suppose the following test performance: 95% of all positive individuals are classified correctly (TPR=0.95) and 95% of all negative individuals are classified correctly (TNR=0.95). In such a case, due to high population imbalance and in spite of having high test accuracy (0.95), the probability that an individual who has been classified as positive is in fact positive is very low: P ( + ∣ C + ) = 0.0095. {\displaystyle P(+\mid C{+})=0.0095.} We can observe how this low probability is reflected in some of the metrics: P 4 = 0.0370 {\displaystyle \mathrm {P} _{4}=0.0370} , F 1 = 0.0188 {\displaystyle \mathrm {F} _{1}=0.0188} , J = 0.9100 {\displaystyle \mathrm {J} =\mathbf {0.9100} } (Informedness / Youden index), M K = 0.0095 {\displaystyle \mathrm {MK} =0.0095} (Markedness). === Example 2: Image recognition — cats vs dogs === Consider the problem of training a neural network based image classifier with only two types of images: those containing dogs (labeled as 0) and those containing cats (labeled as 1). Thus, the goal is to distinguish between the cats and dogs. Suppose that the classifier overpredicts in favour of cats ("positive" samples): 99.99% of cats are classified correctly and only 1% of dogs are classified correctly. Further, suppose that the image dataset consists of 100000 images, 90% of which are pictures of cats and 10% are pictures of dogs. In this situation, the probability that the picture containing dog will be classified correctly is pretty low: P ( C − | − ) = 0.01. {\displaystyle P(C-|-)=0.01.} Not all metrics are notice this low probability: P 4 = 0.0388 {\displaystyle \mathrm {P} _{4}=0.0388} , F 1 = 0.9478 {\displaystyle \mathrm {F} _{1}=\mathbf {0.9478} } , J = 0.0099 {\displaystyle \mathrm {J} =0.0099} (Informedness / Youden index), M K = 0.8183 {\displaystyle \mathrm {MK} =\mathbf {0.8183} } (Markedness).
Read more →
EuroMatrixPlus

The EuroMatrixPlus is a project that ran from March 2009 to February 2012. EuroMatrixPlus succeeded a project called EuroMatrix (September 2006 to February 2009) and continued in further development and improvement of machine translation (MT) systems for languages of the European Union (EU). == Project objectives == EuroMatrixPlus focused on achieving several goals: To continue advance of MT technology (create MT systems for all official EU languages and provide other MT researchers with existing data and infrastructure). To continually expand and investigate different MT approaches and techniques; to stay open to novel combinations of methods of MT. To bring MT to the users. Users post-edit output of statistical models and the system learns from the feedback and improves itself. Two groups of users were aimed at: Professional translators and translation agencies Users who voluntarily translate texts into their native language To contribute to MT research in Europe. To produce sample application for automatic translation of news and web pages and make that application freely accessible. == Outcome == EuroMatrixPlus contributed to MT field in several ways. It continued in development of an open source statistical MT engine Moses. The project worked on research in hybrid approaches to MT (combination of rule-based and statistical techniques). Several “MT Marathons” and annual evaluation campaigns were organized by the project. The project also resulted in releasing of 196 scientific publications. The results of the work were arranged into ten work packages: WP1: Rich Tree-Based Statistical Translation WP2: Hybrid Machine Translation WP3: Advanced Learning Methods for MT WP4: Open Source Tools and Data WP5: "WikiTrans" Translation Environments WP6: Integrated Localisation Workflow WP7: Evaluation Campaign WP8: Project Management and Dissemination WP9: Integrating Slovak Language Resources WP10: HPSG-based Statistical Translation === Software and data === Here is a list of software and data that were released by the project: Appraise – an open source tool for manual evaluation of MT output BURGER – Bulgarian Resource BulTreeBank – Treebank of Bulgarian CSLM toolkit – free tool for training continuous space language models (CSLM) to large tasks Caitra – tool for post-editing MT results Europarl – European Parliament parallel corpus IRSTLM toolkit – tool for training language models Joshua – an open-source statistical machine translation decoder for hierarchical and syntax-based MT MT Server Land – an open-source architecture for MT Moses – statistical MT MultiUN Corpora – parallel corpus extracted from the United Nations Website PCEDT 2.0 – Prague Czech-English Dependency Treebank PEDT 2.0 – English part of the Prague Czech-English Dependency Treebank Slovak corpora – English-Slovak and Czech-Slovak as well as a Slovak-English and a Slovak-Czech parallel corpus Slovak treebank – A dependency treebank TermEx – RBMT-Suited Statistical Terminology Extraction Tool Treex, TectoMT == Funding == The EuroMatrixPlus project was sponsored by EU Information Society Technology program. Total cost of the project was 5 942 121 €, from which the European Union contributed 4 266 896 €. == Project members == To ensure advance in MT, several organizations that are experts in various disciplines (linguistics, computer science, mathematics, translation) were brought together to cooperate on EuroMatrixPlus. The consortium consisted of academic as well as commercial partners. Academic partners were the University of Edinburgh (United Kingdom), DFKI – German Research Centre for Artificial Intelligence (Germany), Charles University (Czech Republic), Johns Hopkins University (United States), University of Le Mans (France), Fondazione Bruno Kessler (Italy), Dublin City University (Ireland). Two institutions joined about one year into the project. These were the L'udovít Štúr Institute of Linguistics (Slovak Republic) and IICT – Institute of Information and Communication Technologies at the Bulgarian Academy of Sciences (Bulgaria). Commercial partners included Lucy Software and Services GmbH (Germany) and CEET s.r.o. (Czech Republic). Coordination of the project was in hands of DFKI with its Language Technology Lab in Saarbrücken. The principal investigator and scientific coordinator was Hans Uszkoreit, a professor of Computational Linguistics at Saarland University.
Read more →
How to Choose an AI Paragraph Rewriter

Comparing the best AI paragraph rewriter? An AI paragraph rewriter is software that uses machine learning to help you get more done — it lowers the barrier so anyone can produce professional output. Privacy matters too: check whether your data trains the model and whether a no-log or enterprise tier is available. Whether you are a beginner or a pro, the right AI paragraph rewriter slots into your workflow and pays for itself fast. Below we compare features, pricing, and real output so you can choose with confidence.
Read more →
Embodied agent

In artificial intelligence, an embodied agent, also sometimes referred to as an interface agent, is an intelligent agent that interacts with the environment through a physical body within that environment. Agents that are represented graphically with a body, for example a human or a cartoon animal, are also called embodied agents, although they have only virtual, not physical, embodiment. A branch of artificial intelligence focuses on empowering such agents to interact autonomously with human beings and the environment. Mobile robots are one example of physically embodied agents; Ananova and Microsoft Agent are examples of graphically embodied agents. Embodied conversational agents are embodied agents (usually with a graphical front-end as opposed to a robotic body) that are capable of engaging in conversation with one another and with humans employing the same verbal and nonverbal means that humans do (such as gesture, facial expression, and so forth). == Embodied conversational agents == Embodied conversational agents are a form of intelligent user interface. Graphically embodied agents aim to unite gesture, facial expression and speech to enable face-to-face communication with users, providing a powerful means of human-computer interaction. == Advantages == Face-to-face communication allows communication protocols that give a much richer communication channel than other means of communicating. It enables pragmatic communication acts such as conversational turn-taking, facial expression of emotions, information structure and emphasis, visualization and iconic gestures, and orientation in a three-dimensional environment. This communication takes place through both verbal and non-verbal channels such as gaze, gesture, spoken intonation and body posture. Research has found that users prefer a non-verbal visual indication of an embodied system's internal state to a verbal indication, demonstrating the value of additional non-verbal communication channels. As well as this, the face-to-face communication involved in interacting with an embodied agent can be conducted alongside another task without distracting the human participants, instead improving the enjoyment of such an interaction. Furthermore, the use of an embodied presentation agent results in improved recall of the presented information. Embodied agents also provide a social dimension to the interaction. Humans willingly ascribe social awareness to computers, and thus interaction with embodied agents follows social conventions, similar to human to human interactions. This social interaction both raises the believably and perceived trustworthiness of agents, and increases the user's engagement with the system. Rickenberg and Reeves found that the presence of an embodied agent on a website increased the level of user trust in that website, but also increased users' anxiety and affected their performance, as if they were being watched by a real human. Another effect of the social aspect of agents is that presentations given by an embodied agent are perceived as being more entertaining and less difficult than similar presentations given without an agent. Research shows that perceived enjoyment, followed by perceived usefulness and ease of use, is the major factor influencing user adoption of embodied agents. A study in January 2004 by Byron Reeves at Stanford demonstrated how digital characters could "enhance online experiences" through explaining how virtual characters essentially add a sense of familiarity to the user experience and make it more approachable. This increase in likability in turn helps make the products better, which benefits both the end users and those creating the product. === Applications === The rich style of communication that characterizes human conversation makes conversational interaction with embodied conversational agents ideal for many non-traditional interaction tasks. A familiar application of graphically embodied agents is computer games; embodied agents are ideal for this setting because the richer communication style makes interacting with the agent enjoyable. Embodied conversational agents have also been used in virtual training environments, portable personal navigation guides, interactive fiction and storytelling systems, interactive online characters and automated presenters and commentators. Major virtual assistants like Siri, Amazon Alexa and Google Assistant do not come with any visual embodied representation, which is believed to limit the sense of human presence by users. The U.S. Department of Defense utilizes a software agent called SGT STAR on U.S. Army-run Web sites and Web applications for site navigation, recruitment and propaganda purposes. Sgt. Star is run by the Army Marketing and Research Group, a division operated directly from The Pentagon. Sgt. Star is based upon the ActiveSentry technology developed by Next IT, a Washington-based information technology services company. Other such bots in the Sgt. Star "family" are utilized by the Federal Bureau of Investigation and the Central Intelligence Agency for intelligence gathering purposes.
Read more →
A Comprehensive Grammar of the English Language

A Comprehensive Grammar of the English Language is a descriptive grammar of English written by Randolph Quirk, Sidney Greenbaum, Geoffrey Leech, and Jan Svartvik. It was first published by Longman in 1985. In 1991, it was called "The greatest of contemporary grammars, because it is the most thorough and detailed we have," and "It is a grammar that transcends national boundaries." The book relies on elicitation experiments as well as three corpora: a corpus from the Survey of English Usage, the Lancaster-Oslo-Bergen Corpus (UK English), and the Brown Corpus (US English). == Reviews == In 1988, Rodney Huddleston published a very critical review. He wrote:[T]here are some respects in which it is seriously flawed and disappointing. A number of quite basic categories and concepts do not seem to have been thought through with sufficient care; this results in a remarkable amount of unclarity and inconsistency in the analysis, and in the organization of the grammar. Aarts, F. G. A. M. (April 1988). "A Comprehensive Grammar of the English Language: The great tradition continued". English Studies. 69 (2): 163–173. doi:10.1080/00138388808598565.
Read more →
Salvatore J. Stolfo

Salvatore J. Stolfo is an academic and professor of computer science at Columbia University, specializing in computer security. == Early life == Born in Brooklyn, New York, Stolfo received a Bachelor of Science degree in Computer Science and Mathematics from Brooklyn College in 1974. He received his Ph.D. from NYU Courant Institute in 1979 and has been on the faculty of Columbia ever since, where he's taught courses in Artificial Intelligence, Intrusion and Anomaly Detection Systems, Introduction to Programming, Fundamental Algorithms, Data Structures, and Knowledge-Based Expert Systems. == Academic research == While at Columbia, Stolfo has received close to $50M in funding for research that has broadly focused on Security, Intrusion Detection, Anomaly Detection, Machine Learning and includes early work in parallel computing and artificial intelligence. He has published or co-authored over 250 papers and has over 46,000 citations with an H-index of 102. In 1996 he proposed a project with DARPA that applies machine learning to behavioral patterns to detect fraud or intrusion in networks. DADO, developed by in part by Stolfo, introduced the parallel computing primitive: “Broadcast, Resolve, Report”, a hardwire implemented mechanism that today is called MapReduce. Among his earliest work, Stolfo along with colleague Greg Vesonder of Bell Labs, developed a large-scale expert data analysis system, called ACE (Automated Cable Expertise) for the nation's phone system. AT&T Bell Labs distributed ACE to a number of telephone wire centers to improve the management and scheduling of repairs in the local loop. Stolfo coined the term FOG computing (not to be confused with fog computing) where technology is used “to launch disinformation attacks against malicious insiders, preventing them from distinguishing the real sensitive customer data from fake worthless data.” In 2005 Stolfo received funding from the Army Research Office to conduct a workshop to bring together a group of researchers to help identify a research program to focus on insider threats. He was elevated to IEEE Fellow in 2018 "for his contributions to machine learning based cybersecurity." He was elected as an ACM Fellow in 2019 "for contributions to machine-learning-based cybersecurity and parallel hardware for database inference systems". == Career == Founded in 2011, Red Balloon Security (or RBS) is a cyber security company founded by Dr Sal Stolfo and Dr Ang Cui. A spinout from the IDS lab, RBS developed a symbiote technology called FRAK as a host defense for embedded systems under the sponsorship of DARPA's Cyber Fast Track program. Created based on their IDS lab research for the DARPA Active Authentication and the Anomaly Detection at Multiple Scales program, Dr Sal Stolfo and Dr. Angelos Keromytis founded Allure Security Technologies. Using active behavioral authentication and decoy technology Stolfo pioneered and patented in 1996. Founded in 2009, Allure Security Technology was created based on work done under DARPA sponsorship in Columbia's IDS lab based on DARPA prompts to research how to detect hackers once they are inside an organization's perimeter and how to continuously authenticate a user without a password. Stolfo's company Electronic Digital Documents produced a “DataBlade” technology, which Informix marketed during their strategy of acquisition and development in the mid 80's. Stolfo's patented merge/purge technology called EDD DataCleanser DataBlade was licensed by Informix. Since its acquisition by IBM in 2005, IBM Informix is one of the world's most widely used database servers, with users ranging from the world's largest corporations to startups. System Detection was one of the companies founded by Prof. Stolfo to commercialize the Anomaly Detection technology developed in the IDS lab. The company ultimately reorganized and was rebranded as Trusted Computer Solutions. That company was recently acquired by Raytheon. Recently a jury awarded Columbia University $185 million for patent infringement for one of Prof. Stolfo's inventions, the Application Communities technology. https://news.columbia.edu/news/columbia-university-awarded-185-million-patent-infringement-nortonlifelock-inc. The final order from the judge applied nearly treble damages: https://www.reuters.com/legal/litigation/gen-digital-owes-columbia-481-mln-us-patent-fight-judge-says-2023-10-02/
Read more →
Boris Katz

Boris Gershevich Katz (Russian: Борис Гершевич Кац; born October 5, 1947) is a principal American research scientist (computer scientist) at the MIT Computer Science and Artificial Intelligence Laboratory at the Massachusetts Institute of Technology in Cambridge and head of the Laboratory's InfoLab Group. His research interests include natural language processing and understanding, machine learning and intelligent information access. His brother Victor Kac is a mathematician at MIT. He was able to get out of the USSR with the help of U.S. Senator Ted Kennedy, before the end of the Cold War. Over the last several decades, Boris Katz has been developing the START natural language system that allows the user to access various types of information using English. == Biography == Boris Katz was born on October 5, 1947, in Chișinău in the family of Hersh Katz (died 1976) and Hayki (Klara) Landman (born 1921, Lipcani, Briceni District - died 2006, Cambridge, Middlesex County), who moved from Lipcani, a town located in the northern Bessarabian, to Chișinău before the war. He graduated from Moscow State University and in November 1978, he left for the United States thanks to the personal intervention of Senator Edward M. Kennedy. He defended his thesis as a candidate of physical and mathematical sciences in 1975 under the supervision of Evgenii M. Landis. He currently lives in Boston and heads the InfoLabresearch team at the Laboratory of Informatics and Artificial Intelligence at the Massachusetts Institute of Technology. Boris Katz is the creator of the START information processing system (since 1993 - on the Internet), the author of several works in the field of processing, generation and perception of natural languages, machine learning, and accelerated access to multimedia information. == Family == Brothers - Victor Gershevich Katz, American mathematician, professor at the Massachusetts Institute of Technology; Mikhail Gershevich Katz, Israeli mathematician, graduate of Harvard and Columbia (Ph.D., 1984) universities, professor at Bar-Ilan University, author of the monograph "Systolic Geometry and Topology" (Mathematical Surveys and Monographs, vol. 137. American Mathematical Society: Providence, 2007). Daughter - Luba Katz, a bioinformatics scientist (her husband is Alan Jasanoff, a neuroimaging scientist, a professor at MIT, the son of Harvard University professors Jay Jasanoff and Sheila Jasanoff). == Past works == A Knowledge Entry System for Subject Matter Experts: The goal of SHAKEN project is to enable subject matter experts, without any assistance from AI technologists, to assemble the models of processes and mechanisms so that questions about them can be answered by declarative inference and simulation. Exploiting lexical regularities in designing natural language systems Word sense disambiguation for information retrieval HIKE (HPKB integrated knowledge environment)- a query interface and integrated knowledge environment for HPKB Quantitative evaluation of passage retrieval algorithms for question answering Sticky notes for the semantic web Question answering from the web using knowledge annotation and knowledge mining techniques The role of context in question answering systems
Read more →
Meta-learning (computer science)

Meta-learning is a subfield of machine learning where automatic learning algorithms are applied to metadata about machine learning experiments. As of 2017, the term had not found a standard interpretation, however the main goal is to use such metadata to understand how automatic learning can become flexible in solving learning problems, hence to improve the performance of existing learning algorithms or to learn (induce) the learning algorithm itself, hence the alternative term learning to learn. Flexibility is important because each learning algorithm is based on a set of assumptions about the data, its inductive bias. This means that it will only learn well if the bias matches the learning problem. A learning algorithm may perform very well in one domain, but not on the next. This poses strong restrictions on the use of machine learning or data mining techniques, since the relationship between the learning problem (often some kind of database) and the effectiveness of different learning algorithms is not yet understood. By using different kinds of metadata, like properties of the learning problem, algorithm properties (like performance measures), or patterns previously derived from the data, it is possible to learn, select, alter or combine different learning algorithms to effectively solve a given learning problem. Critiques of meta-learning approaches bear a strong resemblance to the critique of metaheuristic, a possibly related problem. A good analogy to meta-learning, and the inspiration for Jürgen Schmidhuber's early work (1987) and Yoshua Bengio et al.'s work (1991), considers that genetic evolution learns the learning procedure encoded in genes and executed in each individual's brain. In an open-ended hierarchical meta-learning system using genetic programming, better evolutionary methods can be learned by meta evolution, which itself can be improved by meta meta evolution, etc. == Definition == A proposed definition for a meta-learning system combines three requirements: The system must include a learning subsystem. Experience is gained by exploiting meta knowledge extracted in a previous learning episode on a single dataset, or from different domains. Learning bias must be chosen dynamically. Bias refers to the assumptions that influence the choice of explanatory hypotheses and not the notion of bias represented in the bias-variance dilemma. Meta-learning is concerned with two aspects of learning bias. Declarative bias specifies the representation of the space of hypotheses, and affects the size of the search space (e.g., represent hypotheses using linear functions only). Procedural bias imposes constraints on the ordering of the inductive hypotheses (e.g., preferring smaller hypotheses). == Common approaches == There are three common approaches: using (cyclic) networks with external or internal memory (model-based) learning effective distance metrics (metrics-based) explicitly optimizing model parameters for fast learning (optimization-based). === Model-Based === Model-based meta-learning models updates its parameters rapidly with a few training steps, which can be achieved by its internal architecture or controlled by another meta-learner model. ==== Memory-Augmented Neural Networks ==== A Memory-Augmented Neural Network, or MANN for short, is claimed to be able to encode new information quickly and thus to adapt to new tasks after only a few examples. ==== Meta Networks ==== Meta Networks (MetaNet) learns a meta-level knowledge across tasks and shifts its inductive biases via fast parameterization for rapid generalization. === Metric-Based === The core idea in metric-based meta-learning is similar to nearest neighbors algorithms, which weight is generated by a kernel function. It aims to learn a metric or distance function over objects. The notion of a good metric is problem-dependent. It should represent the relationship between inputs in the task space and facilitate problem solving. ==== Convolutional Siamese Neural Network ==== Siamese neural network is composed of two twin networks whose output is jointly trained. There is a function above to learn the relationship between input data sample pairs. The two networks are the same, sharing the same weight and network parameters. ==== Matching Networks ==== Matching Networks learn a network that maps a small labelled support set and an unlabelled example to its label, obviating the need for fine-tuning to adapt to new class types. ==== Relation Network ==== The Relation Network (RN), is trained end-to-end from scratch. During meta-learning, it learns to learn a deep distance metric to compare a small number of images within episodes, each of which is designed to simulate the few-shot setting. ==== Prototypical Networks ==== Prototypical Networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve satisfied results. === Optimization-Based === What optimization-based meta-learning algorithms intend for is to adjust the optimization algorithm so that the model can be good at learning with a few examples. ==== LSTM Meta-Learner ==== LSTM-based meta-learner is to learn the exact optimization algorithm used to train another learner neural network classifier in the few-shot regime. The parametrization allows it to learn appropriate parameter updates specifically for the scenario where a set amount of updates will be made, while also learning a general initialization of the learner (classifier) network that allows for quick convergence of training. ==== Temporal Discreteness ==== Model-Agnostic Meta-Learning (MAML) is a fairly general optimization algorithm, compatible with any model that learns through gradient descent. ==== Reptile ==== Reptile is a remarkably simple meta-learning optimization algorithm, given that both of its components rely on meta-optimization through gradient descent and both are model-agnostic. == Examples == Some approaches which have been viewed as instances of meta-learning: Recurrent neural networks (RNNs) are universal computers. In 1993, Jürgen Schmidhuber showed how "self-referential" RNNs can in principle learn by backpropagation to run their own weight change algorithm, which may be quite different from backpropagation. In 2001, Sepp Hochreiter & A.S. Younger & P.R. Conwell built a successful supervised meta-learner based on Long short-term memory RNNs. It learned through backpropagation a learning algorithm for quadratic functions that is much faster than backpropagation. Researchers at Deepmind (Marcin Andrychowicz et al.) extended this approach to optimization in 2017. In the 1990s, Meta Reinforcement Learning or Meta RL was achieved in Schmidhuber's research group through self-modifying policies written in a universal programming language that contains special instructions for changing the policy itself. There is a single lifelong trial. The goal of the RL agent is to maximize reward. It learns to accelerate reward intake by continually improving its own learning algorithm which is part of the "self-referential" policy. An extreme type of Meta Reinforcement Learning is embodied by the Gödel machine, a theoretical construct which can inspect and modify any part of its own software which also contains a general theorem prover. It can achieve recursive self-improvement in a provably optimal way. Model-Agnostic Meta-Learning (MAML) was introduced in 2017 by Chelsea Finn et al. Given a sequence of tasks, the parameters of a given model are trained such that few iterations of gradient descent with few training data from a new task will lead to good generalization performance on that task. MAML "trains the model to be easy to fine-tune." MAML was successfully applied to few-shot image classification benchmarks and to policy-gradient-based reinforcement learning. Variational Bayes-Adaptive Deep RL (VariBAD) was introduced in 2019. While MAML is optimization-based, VariBAD is a model-based method for meta reinforcement learning, and leverages a variational autoencoder to capture the task information in an internal memory, thus conditioning its decision making on the task. When addressing a set of tasks, most meta learning approaches optimize the average score across all tasks. Hence, certain tasks may be sacrificed in favor of the average score, which is often unacceptable in real-world applications. By contrast, Robust Meta Reinforcement Learning (RoML) focuses on improving low-score tasks, increasing robustness to the selection of task. RoML works as a meta-algorithm, as it can be applied on top of other meta learning algorithms (such as MAML and VariBAD) to increase their robustness. It is applicable to both supervised meta learning and meta reinforcement learning. Discovering meta-knowledge works by inducing knowledge
Read more →
Michael L. Littman

Michael Lederman Littman (born August 30, 1966) is a computer scientist, researcher, educator, and author. His research interests focus on reinforcement learning. He is currently a University Professor of Computer Science at Brown University, where he has taught since 2012. As of July 2025, he is also the university’s inaugural Associate Provost for Artificial Intelligence. == Career == Before graduate school, Littman worked with Thomas Landauer at Bellcore and was granted a patent for one of the earliest systems for cross-language information retrieval. Littman received his Ph.D. in computer science from Brown University in 1996. From 1996 to 1999, he was a professor at Duke University. During his time at Duke, he worked on an automated crossword solver PROVERB, which won an Outstanding Paper Award in 1999 from AAAI and competed in the American Crossword Puzzle Tournament. From 2000 to 2002, he worked at AT&T. From 2002 to 2012, he was a professor at Rutgers University; he chaired the department from 2009-12. In Summer 2012 he returned to Brown University as a full professor. He has also taught at Georgia Institute of Technology, where he was listed as an adjunct professor. Littman served as the Division Director for Information and Intelligent Systems (the AI division) at the National Science Foundation from 2022-2025. After serving a term, he returned to Brown University as their first Associate Provost for Artificial Intelligence where he coordinates the intersection of AI with research, teaching, operations, policy, and communication at the university level. == Research == Littman's research interests are varied but have focused mostly on reinforcement learning and related fields, particularly, in machine learning more generally, game theory, computer networking, partially observable Markov decision process solving, computer solving of analogy problems and other areas. He is also interested in computing education more broadly and has authored a book on programming for everyone. == Leadership and Service == Littman has chaired the panel for The One Hundred‑Year Study on Artificial Intelligence (AI100) 2021 Report and will chair the standing committee for the 2026 report. During his time at the National Science Foundation, he co-led the development of the 2023 National Strategic Artificial Intelligence Research and Development Strategic Plan. == Personal Notes == Littman is also known for his playful approach to communication. He has produced multiple education and parody videos (for example a machine-learning version of Michael Jackson’s Thriller with his oft-collaborator Charles Lee Isbell, Jr.) as part of his teaching outreach. Among his hobbies, he has been noted riding an electric unicycle to his office at the NSF. == Awards == Elected as an ACM Fellow in 2018 for "contributions to the design and analysis of sequential decision-making algorithms in artificial intelligence". Winner of the IFAAMAS Influential Paper Award (2014) Winner of the AAAI “Shakey” Award for Overfitting: Machine Learning Music Video (2014) Elected as a AAAI Fellow in 2010 for "significant contributions to the fields of reinforcement learning, decision making under uncertainty, and statistical language applications". Winner of the AAAI “Shakey” Award for Short Video for Aibo Ingenuity (2007) Winner of the Warren I. Susman Award for Excellence in Teaching at Rutgers (2011) Winner of the Robert B. Cox Award at Duke (1999) Winner of the AAAI Outstanding Paper Award (1999)
Read more →
Black in AI

Black in AI, formally called the Black in AI Workshop, is a technology research organization and affinity group, founded by computer scientists Timnit Gebru and Rediet Abebe in 2017. It started as a conference workshop, later pivoting into an organization. Black in AI increases the presence and inclusion of Black people in the field of artificial intelligence (AI) by creating space for sharing ideas, fostering collaborations, mentorship, and advocacy. == History == Black in AI was created in 2017 to address issues of lack of diversity in AI workshops, and was started as its own workshop within the Conference on Neural Information Processing Systems (NeurIPS) conference. Because of algorithmic bias, ethical issues, and underrepresentation of Black people in AI roles; there has been an ongoing need for unity within the AI community to have focus on these issues. Black in AI has strived to continue the progress of improving the presence of people of color in the field of artificial intelligence. In 2018 and 2019, the Black in AI workshop had many immigration visa issues to Canada, which spurred the conference to be planned for 2020 in Addis Ababa, Ethiopia. On December 7, 2020, Black in AI held its fourth annual workshop and first virtual workshop (due to the COVID-19 pandemic). In 2021, Black in AI, alongside the groups Queer in AI and Widening NLP, released a public statement refusing funding from Google in an act of protest of Google's treatment of Timnit Gebru, Margaret Mitchell, and April Christina Curley in the events that occurred in December 2020. == Founders == Rediet Abebe is an Ethiopian computer scientist who specializes in algorithms and artificial intelligence. She is a Computer Science Assistant Professor at the University of California, Berkeley. She was previously a Junior Fellow at Harvard's Society of Fellows. She was the first Black woman to receive a Ph.D. in computer science at Cornell University. She "designs and analyzes algorithms, discrete optimizations, network-based, [and] computational strategies to increase access to opportunity for historically disadvantaged populations," according to her web bio. Timnit Gebru was born in Ethiopia and moved to the United States at the age of fifteen. She got her B.S. and M.S. in electrical engineering from Stanford University, as well as a PhD from the Stanford Artificial Intelligence Laboratory, where she studied computer vision under Fei-Fei Li. She formerly worked as a postdoctoral researcher at Microsoft Research in the Fairness Accountability Transparency, and Ethics (FATE) division. She's also worked with Apple, where she assisted in the development of signal-processing algorithms for the original iPad. == Grants == Black in AI received grants and support from private foundations like MacArthur Foundation and Rockefeller Foundation. The organization received $10,000 in 2018 for its annual workshop and $150,000 in 2019 for its long-term organizational planning. In 2020, during the pandemic, the organization received a grant of $300,000 by MacArthur Foundation in order to provide broad organizational support. In 2022, Rockefeller Foundation announced $300,000 to fight prejudice in artificial intelligence (AI) across the globe and incorporate equity into this rapidly expanding field. == Programs == "Black in AI works in academics, advocacy, entrepreneurship, financial support, and summer research programs." The Black in AI Academic Program is a resource for Black junior researchers applying to graduate schools, navigating graduate school, and transitioning into the postgraduate employment market. They provide online education sessions, offer scholarships to cover application fees, pair participants with peer and senior mentors, and distribute crowdsourced papers that simplify the application process. They also undertake research projects to investigate and highlight the difficulties that Black young researchers face, as well as push for structural reforms to eliminate these barriers and build equitable research settings. Moses Namara is a Facebook Research Fellow at Clemson University and a PhD candidate in Human-Centered Computing (HCC). He is the mentor for the new Black in AI Academic Program. During the graduate school admissions season in 2021, Black in AI served more than 200 potential graduate program candidates in some capacity. Furthermore, the organization's study identified greater problems encountered by Black graduate school candidates, such as the high cost of graduate school admissions examinations (GREs), which are known to be biased against those from low-income backgrounds. Black in AI's attempts to encourage institutions to eliminate the obstacles were supported by the findings. Black in AI is also developing a program to help and connect Black tech startups with investors. Black in AI also mentors early-career Black AI academics and is forming relationships with Historically Black Colleges and Universities to extend its academic program. In 2021, Black in AI launched two summer research programs, one for undergraduate internships and another for unconstrained research mentorship, including one aimed explicitly at empowering Black women's AI research projects. == Conferences and workshops == At NeurIPS 2017, the first Black in AI event took place in December 8, 2017 in Long Beach, California. The goal was to bring together experts in the area to share ideas and debate efforts aimed at increasing the participation of Black people in artificial intelligence, both for diversity and to avoid data bias. Black AI researchers had the opportunity to share their work at the workshop's oral and poster sessions. The second workshop was hosted in Montréal, Canada, on December 7, 2018. According to AI experts, visa issues stymie efforts to make their area more inclusive, making technology that discriminates or disadvantages individuals who aren't white or Western less likely. Hundreds of participants who were supposed to attend or present work at the Black in AI session on Friday were unable to fly to Canada; many of the participants were from African countries. The third workshop was held in NeurIPS 2019, one of the premier machine learning conferences Vancouver, Canada. The workshop was able to give travel scholarships and visa support to hundreds of academics who would not have been able to attend NeurIPS without the help of sponsors. For instance, Ramon Vilarino of the University of Sao Paulo, who presented a poster at the conference on his study of geographical and racial prejudice in credit scoring in Brazil, would not have been able to attend NeurIPS without the help of Black in AI. Twenty-four academics from Africa and South America were denied visas to attend this session during the conference, according to Victor Silva, the workshop organizer. He noted that, less than a month before the conference, 40 applicants from both continents had been given visas but that more than 70 applications were still waiting. For the second year in a row, visa restrictions have stopped several African scholars from attending the 2018 meeting in Montreal. The AAAI announced the first Black in AI lunch, which was held in conjunction with AAAI-19. The lunch was hosted on Tuesday, January 29, 2019. This event was intended to promote networking, discussion of various AI career options, and the exchange of ideas in order to boost the number of Black researchers in the area. The fourth Black in AI workshop, which was held in conjunction with NeurIPS 2020, took place the week of December 7, 2020. The workshop was scheduled to take place in Vancouver, British Columbia. Due to the pandemic, the session was held for the first time in a virtual format. Victor Silva, an AI4Society student, served as the event's chair. The fifth annual Black in AI workshop was also held virtually in 2021. Oral presentations, guest keynote speakers, a combined poster session with other affinity groups, sponsored sessions, and startup showcases was all featured. The goal of the session was to raise the visibility of black scholars at NeurIPS.
Read more →