AI Face Grader

AI Face Grader — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

  • TAChart

    TAChart

    TAChart is a component for the Lazarus IDE that provides charting services. Similar to Tchart and Teechart for Delphi it supports a collection of different chart types including bar charts, pie charts, line charts and point series. Apart from a screen canvas, output is possible in form of SVG, OpenGL, printer, WMF, and other formats. TAChart is bundled with the Lazarus Component Library. Although not intended to be a TChart clone, why its usage differs in certain points, its basic functionality is very similar and some source code written for TeeChart may be reused. == History == The first version of TAChart was developed by Philippe Martinole for the TeleAuto project, a program for automation of astronomic observations. Later functionality was introduced by Luis Rodrigues while porting the Epanet application from Delphi to Lazarus. In the ensuing years the code has extensively rewritten, expanded and is now maintained by Alexander Klenin. == Data sources == TAChart is able to use input from various sources. Examples include lists of real values, user defined buffers in the computer's memory, vectors of random values, fields in databases, calculated values provided by pre-defined functions and results of embedded code written in Pascal Script

    Read more →
  • AI Resume Builders: Free vs Paid (2026)

    AI Resume Builders: Free vs Paid (2026)

    Comparing the best AI resume builder? An AI resume builder 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 resume builder 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 →
  • Imitation learning

    Imitation learning

    Imitation learning is a paradigm in reinforcement learning, where an agent learns to perform a task by supervised learning from expert demonstrations . It is also called learning from demonstration and apprenticeship learning. It has been applied to underactuated robotics, self-driving cars, quadcopter navigation, helicopter aerobatics, and locomotion. == Approaches == Expert demonstrations are recordings of an expert performing the desired task, often collected as state-action pairs ( o t ∗ , a t ∗ ) {\displaystyle (o_{t}^{},a_{t}^{})} . === Behavior Cloning === Behavior Cloning (BC) is the most basic form of imitation learning. Essentially, it uses supervised learning to train a policy π θ {\displaystyle \pi _{\theta }} such that, given an observation o t {\displaystyle o_{t}} , it would output an action distribution π θ ( ⋅ | o t ) {\displaystyle \pi _{\theta }(\cdot |o_{t})} that is approximately the same as the action distribution of the experts. BC is susceptible to distribution shift. Specifically, if the trained policy differs from the expert policy, it might find itself straying from expert trajectory into observations that would have never occurred in expert trajectories. This was already noted by ALVINN, where they trained a neural network to drive a van using human demonstrations. They noticed that because a human driver never strays far from the path, the network would never be trained on what action to take if it ever finds itself straying far from the path. === DAgger === DAgger (Dataset Aggregation) improves on behavior cloning by iteratively training on a dataset of expert demonstrations. In each iteration, the algorithm first collects data by rolling out the learned policy π θ {\displaystyle \pi _{\theta }} . Then, it queries the expert for the optimal action a t ∗ {\displaystyle a_{t}^{}} on each observation o t {\displaystyle o_{t}} encountered during the rollout. Finally, it aggregates the new data into the dataset D ← D ∪ { ( o 1 , a 1 ∗ ) , ( o 2 , a 2 ∗ ) , . . . , ( o T , a T ∗ ) } {\displaystyle D\leftarrow D\cup \{(o_{1},a_{1}^{}),(o_{2},a_{2}^{}),...,(o_{T},a_{T}^{})\}} and trains a new policy on the aggregated dataset. === Decision transformer === The Decision Transformer approach models reinforcement learning as a sequence modelling problem. Similar to Behavior Cloning, it trains a sequence model, such as a Transformer, that models rollout sequences ( R 1 , o 1 , a 1 ) , ( R 2 , o 2 , a 2 ) , … , ( R t , o t , a t ) , {\displaystyle (R_{1},o_{1},a_{1}),(R_{2},o_{2},a_{2}),\dots ,(R_{t},o_{t},a_{t}),} where R t = r t + r t + 1 + ⋯ + r T {\displaystyle R_{t}=r_{t}+r_{t+1}+\dots +r_{T}} is the sum of future reward in the rollout. During training time, the sequence model is trained to predict each action a t {\displaystyle a_{t}} , given the previous rollout as context: ( R 1 , o 1 , a 1 ) , ( R 2 , o 2 , a 2 ) , … , ( R t , o t ) {\displaystyle (R_{1},o_{1},a_{1}),(R_{2},o_{2},a_{2}),\dots ,(R_{t},o_{t})} During inference time, to use the sequence model as an effective controller, it is simply given a very high reward prediction R {\displaystyle R} , and it would generalize by predicting an action that would result in the high reward. This was shown to scale predictably to a Transformer with 1 billion parameters that is superhuman on 41 Atari games. === Other approaches === See for more examples. == Related approaches == Inverse Reinforcement Learning (IRL) learns a reward function that explains the expert's behavior and then uses reinforcement learning to find a policy that maximizes this reward. Recent works have also explored multi-agent extensions of IRL in networked systems. Generative Adversarial Imitation Learning (GAIL) uses generative adversarial networks (GANs) to match the distribution of agent behavior to the distribution of expert demonstrations. It extends a previous approach using game theory.

    Read more →
  • AI Marketing Tools Reviews: What Actually Works in 2026

    AI Marketing Tools Reviews: What Actually Works in 2026

    In search of the best AI marketing tool? An AI marketing tool is software that uses machine learning to help you get more done — it turns a rough idea into a polished result in seconds. When choosing one, weigh output quality, pricing, export formats, and how well it fits the tools you already use. Whether you are a beginner or a pro, the right AI marketing tool slots into your workflow and pays for itself fast. We tested the leading options and ranked them by quality, value, and ease of use.

    Read more →
  • Data access layer

    Data access layer

    A data access layer (DAL) is a software architectural layer that provides access to data from one or more sources, such as a relational database, NoSQL database, SQL query engine, file system, or other persistent storage. It separates client code from the details of storage systems, query execution, connection handling, and data retrieval. Data access layers are commonly used to centralize data access logic, reduce coupling between applications and data sources, and provide a consistent interface for retrieving, writing, or querying data. Depending on the system, a data access layer may be implemented as application code, a shared library, an intermediary service, or part of a broader database abstraction layer. == In application architecture == In application software, a data access layer provides a boundary between business logic or application code and the systems used to store or retrieve data. For example, a data access layer may expose methods or interfaces for retrieving, writing, or querying data while hiding details such as connection management, SQL statements, storage APIs, error handling, and result conversion. Depending on the application, the layer may return objects, records, tabular results, documents, streams, or other representations of data. A common implementation is a set of classes, functions, or methods that directly reference database queries, stored procedures, storage APIs, or other data sources. For example, instead of using commands such as insert, delete, and update throughout an application to access a specific table, methods such as registerUser or loginUser may be implemented inside the data access layer. Business logic methods from an application can also be mapped to the data access layer. Instead of making several database queries directly, an application can call a single DAL method that abstracts those database calls. Applications using a data access layer may be either dependent on or independent from a particular database server. If the data access layer supports multiple database systems, the application can use any database system that the DAL can access. In either case, the data access layer provides a centralized location for calls into the underlying data store, which can make it easier to maintain, test, or port the application to other storage systems. == Implementation patterns == A data access layer can be implemented using several patterns and technologies, including data access objects, repositories, stored procedures, query builders, database drivers, or object–relational mapping tools. These mechanisms may implement part or all of a data access layer, but are not always equivalent to the layer itself. Object–relational mapping tools are commonly used in data access layers for object-oriented applications that map records in a relational database to objects in a programming language. Other data access layers may expose lower-level database interfaces, tabular results, document-oriented data, files, streams, or protocol-level interfaces. == Use with multiple underlying data systems == A data access layer may be used to abstract differences between multiple underlying data systems, allowing applications to access them through a more consistent interface. In such designs, applications call the DAL rather than interacting directly with each database or storage system. The layer may then handle connection management, query generation, result mapping, error handling, and other implementation details. A data access layer may be implemented as a shared library or as an intermediary service, such as a proxy or gateway. In this configuration, client applications or services connect to the data access layer, which then communicates with one or more underlying databases or query engines. This can provide a common location for authentication, authorization, logging, routing, and translation between different database interfaces. == Interfaces and protocols == Data access layers may expose or use standardized interfaces and protocols for database access. Examples include Open Database Connectivity (ODBC), Java Database Connectivity (JDBC), database-native wire protocols, and newer interfaces such as Apache Arrow Database Connectivity (ADBC) and Arrow Flight SQL. In systems that support multiple data stores, a data access layer may provide a consistent interface while using different drivers, protocols, or query mechanisms internally. == Distinction from related patterns == A data access layer is related to, but broader than, a data access object, which is usually an object-oriented design pattern for encapsulating access to a persistence mechanism. It is also related to a database abstraction layer, which focuses on hiding differences between database systems. In practice, the terms may overlap.

    Read more →
  • Suffix automaton

    Suffix automaton

    In computer science, a suffix automaton is an efficient data structure for representing the substring index of a given string which allows the storage, processing, and retrieval of compressed information about all its substrings. The suffix automaton of a string S {\displaystyle S} is the smallest directed acyclic graph with a dedicated initial vertex and a set of "final" vertices, such that paths from the initial vertex to final vertices represent the suffixes of the string. In terms of automata theory, a suffix automaton is the minimal partial deterministic finite automaton that recognizes the set of suffixes of a given string S = s 1 s 2 … s n {\displaystyle S=s_{1}s_{2}\dots s_{n}} . The state graph of a suffix automaton is called a directed acyclic word graph (DAWG), a term that is also sometimes used for any deterministic acyclic finite state automaton. Suffix automata were introduced in 1983 by a group of scientists from the University of Denver and the University of Colorado Boulder. They suggested a linear time online algorithm for its construction and showed that the suffix automaton of a string S {\displaystyle S} having length at least two characters has at most 2 | S | − 1 {\textstyle 2|S|-1} states and at most 3 | S | − 4 {\textstyle 3|S|-4} transitions. Further works have shown a close connection between suffix automata and suffix trees, and have outlined several generalizations of suffix automata, such as compacted suffix automaton obtained by compression of nodes with a single outgoing arc. Suffix automata provide efficient solutions to problems such as substring search and computation of the largest common substring of two and more strings. == History == The concept of suffix automaton was introduced in 1983 by a group of scientists from University of Denver and University of Colorado Boulder consisting of Anselm Blumer, Janet Blumer, Andrzej Ehrenfeucht, David Haussler and Ross McConnell, although similar concepts had earlier been studied alongside suffix trees in the works of Peter Weiner, Vaughan Pratt and Anatol Slissenko. In their initial work, Blumer et al. showed a suffix automaton built for the string S {\displaystyle S} of length greater than 1 {\displaystyle 1} has at most 2 | S | − 1 {\displaystyle 2|S|-1} states and at most 3 | S | − 4 {\displaystyle 3|S|-4} transitions, and suggested a linear algorithm for automaton construction. In 1983, Mu-Tian Chen and Joel Seiferas independently showed that Weiner's 1973 suffix-tree construction algorithm while building a suffix tree of the string S {\displaystyle S} constructs a suffix automaton of the reversed string S R {\textstyle S^{R}} as an auxiliary structure. In 1987, Blumer et al. applied the compressing technique used in suffix trees to a suffix automaton and invented the compacted suffix automaton, which is also called the compacted directed acyclic word graph (CDAWG). In 1997, Maxime Crochemore and Renaud Vérin developed a linear algorithm for direct CDAWG construction. In 2001, Shunsuke Inenaga et al. developed an algorithm for construction of CDAWG for a set of words given by a trie. == Definitions == Usually when speaking about suffix automata and related concepts, some notions from formal language theory and automata theory are used, in particular: "Alphabet" is a finite set Σ {\displaystyle \Sigma } that is used to construct words. Its elements are called "characters"; "Word" is a finite sequence of characters ω = ω 1 ω 2 … ω n {\displaystyle \omega =\omega _{1}\omega _{2}\dots \omega _{n}} . "Length" of the word ω {\displaystyle \omega } is denoted as | ω | = n {\displaystyle |\omega |=n} ; "Formal language" is a set of words over given alphabet; "Language of all words" is denoted as Σ ∗ {\displaystyle \Sigma ^{}} (where the "" character stands for Kleene star), "empty word" (the word of zero length) is denoted by the character ε {\displaystyle \varepsilon } ; "Concatenation of words" α = α 1 α 2 … α n {\displaystyle \alpha =\alpha _{1}\alpha _{2}\dots \alpha _{n}} and β = β 1 β 2 … β m {\displaystyle \beta =\beta _{1}\beta _{2}\dots \beta _{m}} is denoted as α ⋅ β {\displaystyle \alpha \cdot \beta } or α β {\displaystyle \alpha \beta } and corresponds to the word obtained by writing β {\displaystyle \beta } to the right of α {\displaystyle \alpha } , that is, α β = α 1 α 2 … α n β 1 β 2 … β m {\displaystyle \alpha \beta =\alpha _{1}\alpha _{2}\dots \alpha _{n}\beta _{1}\beta _{2}\dots \beta _{m}} ; "Concatenation of languages" A {\displaystyle A} and B {\displaystyle B} is denoted as A ⋅ B {\displaystyle A\cdot B} or A B {\displaystyle AB} and corresponds to the set of pairwise concatenations A B = { α β : α ∈ A , β ∈ B } {\displaystyle AB=\{\alpha \beta :\alpha \in A,\beta \in B\}} ; If the word ω ∈ Σ ∗ {\displaystyle \omega \in \Sigma ^{}} may be represented as ω = α γ β {\displaystyle \omega =\alpha \gamma \beta } , where α , β , γ ∈ Σ ∗ {\displaystyle \alpha ,\beta ,\gamma \in \Sigma ^{}} , then words α {\displaystyle \alpha } , β {\displaystyle \beta } and γ {\displaystyle \gamma } are called "prefix", "suffix" and "subword" (substring) of the word ω {\displaystyle \omega } correspondingly; If T = T 1 … T n {\displaystyle T=T_{1}\dots T_{n}} and T l T l + 1 … T r = S {\displaystyle T_{l}T_{l+1}\dots T_{r}=S} (with 1 ≤ l ≤ r ≤ n {\displaystyle 1\leq l\leq r\leq n} ) then S {\displaystyle S} is said to "occur" in T {\displaystyle T} as a subword. Here l {\displaystyle l} and r {\displaystyle r} are called left and right positions of occurrence of S {\displaystyle S} in T {\displaystyle T} correspondingly. == Automaton structure == Formally, deterministic finite automaton is determined by 5-tuple A = ( Σ , Q , q 0 , F , δ ) {\displaystyle {\mathcal {A}}=(\Sigma ,Q,q_{0},F,\delta )} , where: Σ {\displaystyle \Sigma } is an "alphabet" that is used to construct words, Q {\displaystyle Q} is a set of automaton "states", q 0 ∈ Q {\displaystyle q_{0}\in Q} is an "initial" state of automaton, F ⊂ Q {\displaystyle F\subset Q} is a set of "final" states of automaton, δ : Q × Σ ↦ Q {\displaystyle \delta :Q\times \Sigma \mapsto Q} is a partial "transition" function of automaton, such that δ ( q , σ ) {\displaystyle \delta (q,\sigma )} for q ∈ Q {\displaystyle q\in Q} and σ ∈ Σ {\displaystyle \sigma \in \Sigma } is either undefined or defines a transition from q {\displaystyle q} over character σ {\displaystyle \sigma } . Most commonly, deterministic finite automaton is represented as a directed graph ("diagram") such that: Set of graph vertices corresponds to the state of states Q {\displaystyle Q} , Graph has a specific marked vertex corresponding to initial state q 0 {\displaystyle q_{0}} , Graph has several marked vertices corresponding to the set of final states F {\displaystyle F} , Set of graph arcs corresponds to the set of transitions δ {\displaystyle \delta } , Specifically, every transition δ ( q 1 , σ ) = q 2 {\textstyle \delta (q_{1},\sigma )=q_{2}} is represented by an arc from q 1 {\displaystyle q_{1}} to q 2 {\displaystyle q_{2}} marked with the character σ {\displaystyle \sigma } . This transition also may be denoted as q 1 σ ⟶ q 2 {\textstyle q_{1}{\begin{smallmatrix}{\sigma }\\[-5pt]{\longrightarrow }\end{smallmatrix}}q_{2}} . In terms of its diagram, the automaton recognizes the word ω = ω 1 ω 2 … ω m {\displaystyle \omega =\omega _{1}\omega _{2}\dots \omega _{m}} only if there is a path from the initial vertex q 0 {\displaystyle q_{0}} to some final vertex q ∈ F {\displaystyle q\in F} such that concatenation of characters on this path forms ω {\displaystyle \omega } . The set of words recognized by an automaton forms a language that is set to be recognized by the automaton. In these terms, the language recognized by a suffix automaton of S {\displaystyle S} is the language of its (possibly empty) suffixes. === Automaton states === "Right context" of the word ω {\displaystyle \omega } with respect to language L {\displaystyle L} is a set [ ω ] R = { α : ω α ∈ L } {\displaystyle [\omega ]_{R}=\{\alpha :\omega \alpha \in L\}} that is a set of words α {\displaystyle \alpha } such that their concatenation with ω {\displaystyle \omega } forms a word from L {\displaystyle L} . Right contexts induce a natural equivalence relation [ α ] R = [ β ] R {\displaystyle [\alpha ]_{R}=[\beta ]_{R}} on the set of all words. If language L {\displaystyle L} is recognized by some deterministic finite automaton, there exists unique up to isomorphism automaton that recognizes the same language and has the minimum possible number of states. Such an automaton is called a minimal automaton for the given language L {\displaystyle L} . Myhill–Nerode theorem allows it to define it explicitly in terms of right contexts: In these terms, a "suffix automaton" is the minimal deterministic finite automaton recognizing the language of suffixes of the word S = s 1 s 2 … s n {\displaystyle S=s_{1}s_{2}\dots s_{n}} . The right context of the word ω {\displaystyle \omeg

    Read more →
  • Top 10 AI Text-to-image Tools Compared (2026)

    Top 10 AI Text-to-image Tools Compared (2026)

    Comparing the best AI text-to-image tool? An AI text-to-image tool 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 text-to-image tool 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 →
  • Karsten Borgwardt

    Karsten Borgwardt

    Karsten Borgwardt (born 1980) is a German computer scientist and biologist specializing in machine learning and computational biology. Since February 2023, he has been a director at the Max Planck Institute of Biochemistry in Martinsried, Germany, where he leads the Department of Machine Learning and Systems Biology. == Education and career == Borgwardt was born in Kaiserslautern. He obtained a Diplom (equivalent to a master’s degree) in computer science from LMU Munich in 2004 and a Master of Science in biology from the University of Oxford in 2003. In 2007, he obtained his PhD from LMU Munich in computer science. Following a postdoctoral position at the University of Cambridge, he became a research group leader for machine learning and computational biology at the Max Planck Institute for Biological Cybernetics and the former Max Planck Institute for Developmental Biology in Tübingen in 2008. In 2011, Borgwardt was appointed professor of data mining in the life sciences at the University of Tübingen. In 2014, he joined ETH Zurich as an associate professor in the Department of Biosystems Science and Engineering (D-BSSE) and was promoted to full professor in 2017. During his tenure at ETH Zurich, he coordinated significant research programs, including two Marie Curie Innovative Training Networks and the Personalized Swiss Sepsis Study, focusing on the prediction of sepsis using machine learning. In 2023, he was appointed as Scientific Member of the Max Planck Society and as Director at the Max Planck Institute of Biochemistry in Martinsried. == Research contributions == Borgwardt’s research integrates big data analysis with biomedical research. He develops novel machine learning algorithms to detect patterns and statistical dependencies in large biological and medical datasets. His work aims to enable the automatic generation of new knowledge from big data and to understand the relationship between the function of biological systems and their molecular properties, which is fundamental for personalized medicine. == Awards and honors == During his studies, he was a scholar of the Stiftung Maximilianeum, and the Bavarian Foundation for the Promotion of the Gifted. Borgwardt received scholarships from the Studienstiftung des deutschen Volkes in 2002 and 2007. His PhD dissertation received the Heinz Schwärtzel Dissertation Award for Foundations of Computer Science in 2007. As a professor in Tübingen, he was awarded the Alfried-Krupp-Förderpreis for Young Professors in 2013. In 2015, he received an SNSF Starting Grant. In 2014, 2015 and 2016, he was listed in “Top 40 under 40” in Germany rankings selected by Capital magazine. In 2018, Borgwardt was named among “25 individuals who have the potential to shape the next 25 years” by Focus magazine. In 2023, Borgwardt received an honorary professorship from LMU Munich by the Faculty of Chemistry and Pharmacy. Publications from Borgwardt's group have received the Outstanding Student Paper Award in NIPS in 2009, the SIB Graduate Paper Award in 2020 and SIB Remarkable Output Awards in 2020 and 2021 from the Swiss Institute of Bioinformatics (SIB). == Selected publications == Weisfeiler-Lehman Graph Kernels (’‘Journal of Machine Learning Research’’, 2011): Introduced an efficient graph kernel based on the Weisfeiler-Lehman algorithm. “Direct antimicrobial resistance prediction from clinical MALDI-TOF mass spectra using machine learning” (’‘Nature Medicine’’, 2022): showcased the feasibility of predicting antimicrobial resistance from readily collected mass spectrometry data in the hospital. The new method is able to identify antibiotic resistance 24 hours earlier than previous methods.

    Read more →
  • International Medical Education Directory

    International Medical Education Directory

    The International Medical Education Directory (IMED) was a public database of worldwide medical schools. The IMED was published as a joint collaboration of the Educational Commission for Foreign Medical Graduates (ECFMG) and the Foundation for Advancement of International Medical Education and Research (FAIMER). The information available in IMED was derived from data collected by the Educational Commission for Foreign Medical Graduates (ECFMG) throughout its history of evaluating the medical education credentials of international medical graduates. Using these data as a starting point, Foundation for Advancement of International Medical Education and Research (FAIMER) began developing IMED in 2001 and made it publicly available in April 2002. In April 2014, IMED was merged with the Avicenna Directory to create the World Directory of Medical Schools. The World Directory is now the definitive list of medical schools in the world, as IMED and Avicenna were discontinued in 2015.

    Read more →
  • Scott Fahlman

    Scott Fahlman

    Scott Elliott Fahlman (born March 21, 1948) is an American computer scientist and Professor Emeritus at Carnegie Mellon University's Language Technologies Institute and Computer Science Department. He is notable for early work on automated planning and scheduling in a blocks world, on semantic networks, on neural networks (especially the cascade correlation algorithm), on the programming languages Dylan, and Common Lisp (especially CMU Common Lisp), and he was one of the founders of Lucid Inc. During the period when it was standardized, he was recognized as "the leader of Common Lisp." From 2006 to 2015, Fahlman was engaged in developing a knowledge base named Scone, based in part on his thesis work on the NETL Semantic Network. He also is credited with coining the use of the emoticon. == Life and career == Fahlman was born in Medina, Ohio, the son of Lorna May (Dean) and John Emil Fahlman. He attended the Massachusetts Institute of Technology (MIT), where he received a Bachelor of Science (B.S.) and Master of Science (M.S.) degree in electrical engineering and computer science in 1973, and a Doctor of Philosophy (Ph.D.) in artificial intelligence in 1977. He has noted that his doctoral diploma says the degree was awarded for "original research as demonstrated by a thesis in the field of Artificial Intelligence" and suggested that it may be the first doctorate to use that term. He is a fellow of the American Association for Artificial Intelligence. Fahlman acted as thesis advisor for Donald Cohen, David B. McDonald, David S. Touretzky, Skef Wholey, Justin Boyan, Michael Witbrock, and Alicia Tribble Sagae. From May 1996 to July 2001, Fahlman directed the Justsystem Pittsburgh Research Center. === Boltzmann Machine (1983) === In 1983, Fahlman, Geoffrey Hinton, and Terry Sejnowski published a paper in Proceedings of the AAAI-83 Conference, Washington DC, August 1983. The paper was titled as "Massively Parallel Architectures for AI: NETL, Thistle and Boltzmann Machines". === Emoticons === Fahlman was not the first to suggest the concept of the emoticon – a similar concept for a marker appeared in an article of Reader's Digest in May 1967, although that idea was never put into practice. In an interview printed in The New York Times in 1969, Vladimir Nabokov noted: "I often think there should exist a special typographical sign for a smile – some sort of concave mark, a supine round bracket." Fahlman is credited with originating the first smiley emoticon, which he thought would help people on a message board at Carnegie Mellon to distinguish serious posts from jokes. He proposed the use of :-) and :-( for this purpose, and the symbols caught on. The original message from which these symbols originated was posted on 19 September 1982. The message was recovered by Jeff Baird on 10 September 2002 and read: 19-Sep-82 11:44 Scott E Fahlman :-) From: Scott E Fahlman I propose that the following character sequence for joke markers: :-) Read it sideways. Actually, it is probably more economical to mark things that are NOT jokes, given current trends. For this, use :-(

    Read more →
  • Restricted Boltzmann machine

    Restricted Boltzmann machine

    A restricted Boltzmann machine (RBM) (also called a restricted Sherrington–Kirkpatrick model with external field or restricted stochastic Ising–Lenz–Little model) is a generative stochastic artificial neural network that can learn a probability distribution over its set of inputs. RBMs were initially proposed under the name Harmonium by Paul Smolensky in 1986, and rose to prominence after Geoffrey Hinton and collaborators used fast learning algorithms for them in the mid-2000s. RBMs have found applications in dimensionality reduction, classification, collaborative filtering, feature learning, topic modelling, immunology, and even many‑body quantum mechanics. They can be trained in either supervised or unsupervised ways, depending on the task. As their name implies, RBMs are a variant of Boltzmann machines, with the restriction that their neurons must form a bipartite graph: a pair of nodes from each of the two groups of units (commonly referred to as the "visible" and "hidden" units respectively) may have a symmetric connection between them; and there are no connections between nodes within a group. By contrast, "unrestricted" Boltzmann machines may have connections between hidden units. This restriction allows for more efficient training algorithms than are available for the general class of Boltzmann machines, in particular the gradient-based contrastive divergence algorithm. Restricted Boltzmann machines can also be used in deep learning networks. In particular, deep belief networks can be formed by "stacking" RBMs and optionally fine-tuning the resulting deep network with gradient descent and backpropagation. == Structure == The standard type of RBM has binary-valued (Boolean) hidden and visible units, and consists of a matrix of weights W {\displaystyle W} of size m × n {\displaystyle m\times n} . Each weight element ( w i , j ) {\displaystyle (w_{i,j})} of the matrix is associated with the connection between the visible (input) unit v i {\displaystyle v_{i}} and the hidden unit h j {\displaystyle h_{j}} . In addition, there are bias weights (offsets) a i {\displaystyle a_{i}} for v i {\displaystyle v_{i}} and b j {\displaystyle b_{j}} for h j {\displaystyle h_{j}} . Given the weights and biases, the energy of a configuration (pair of Boolean vectors) (v,h) is defined as E ( v , h ) = − ∑ i a i v i − ∑ j b j h j − ∑ i ∑ j v i w i , j h j {\displaystyle E(v,h)=-\sum _{i}a_{i}v_{i}-\sum _{j}b_{j}h_{j}-\sum _{i}\sum _{j}v_{i}w_{i,j}h_{j}} or, in matrix notation, E ( v , h ) = − a T v − b T h − v T W h . {\displaystyle E(v,h)=-a^{\mathrm {T} }v-b^{\mathrm {T} }h-v^{\mathrm {T} }Wh.} This energy function is analogous to that of a Hopfield network. As with general Boltzmann machines, the joint probability distribution for the visible and hidden vectors is defined in terms of the energy function as follows, P ( v , h ) = 1 Z e − E ( v , h ) {\displaystyle P(v,h)={\frac {1}{Z}}e^{-E(v,h)}} where Z {\displaystyle Z} is a partition function defined as the sum of e − E ( v , h ) {\displaystyle e^{-E(v,h)}} over all possible configurations, which can be interpreted as a normalizing constant to ensure that the probabilities sum to 1. The marginal probability of a visible vector is the sum of P ( v , h ) {\displaystyle P(v,h)} over all possible hidden layer configurations, P ( v ) = 1 Z ∑ { h } e − E ( v , h ) {\displaystyle P(v)={\frac {1}{Z}}\sum _{\{h\}}e^{-E(v,h)}} , and vice versa. Since the underlying graph structure of the RBM is bipartite (meaning there are no intra-layer connections), the hidden unit activations are mutually independent given the visible unit activations. Conversely, the visible unit activations are mutually independent given the hidden unit activations. That is, for m visible units and n hidden units, the conditional probability of a configuration of the visible units v, given a configuration of the hidden units h, is P ( v | h ) = ∏ i = 1 m P ( v i | h ) {\displaystyle P(v|h)=\prod _{i=1}^{m}P(v_{i}|h)} . Conversely, the conditional probability of h given v is P ( h | v ) = ∏ j = 1 n P ( h j | v ) {\displaystyle P(h|v)=\prod _{j=1}^{n}P(h_{j}|v)} . The individual activation probabilities are given by P ( h j = 1 | v ) = σ ( b j + ∑ i = 1 m w i , j v i ) {\displaystyle P(h_{j}=1|v)=\sigma \left(b_{j}+\sum _{i=1}^{m}w_{i,j}v_{i}\right)} and P ( v i = 1 | h ) = σ ( a i + ∑ j = 1 n w i , j h j ) {\displaystyle \,P(v_{i}=1|h)=\sigma \left(a_{i}+\sum _{j=1}^{n}w_{i,j}h_{j}\right)} where σ {\displaystyle \sigma } denotes the logistic sigmoid. The visible units of Restricted Boltzmann Machine can be multinomial, although the hidden units are Bernoulli. In this case, the logistic function for visible units is replaced by the softmax function P ( v i k = 1 | h ) = exp ⁡ ( a i k + Σ j W i j k h j ) Σ k ′ = 1 K exp ⁡ ( a i k ′ + Σ j W i j k ′ h j ) {\displaystyle P(v_{i}^{k}=1|h)={\frac {\exp(a_{i}^{k}+\Sigma _{j}W_{ij}^{k}h_{j})}{\Sigma _{k'=1}^{K}\exp(a_{i}^{k'}+\Sigma _{j}W_{ij}^{k'}h_{j})}}} where K is the number of discrete values that the visible values have. They are applied in topic modeling, and recommender systems. === Relation to other models === Restricted Boltzmann machines are a special case of Boltzmann machines and Markov random fields. The graphical model of RBMs corresponds to that of factor analysis. == Training algorithm == Restricted Boltzmann machines are trained to maximize the product of probabilities assigned to some training set V {\displaystyle V} (a matrix, each row of which is treated as a visible vector v {\displaystyle v} ), arg ⁡ max W ∏ v ∈ V P ( v ) {\displaystyle \arg \max _{W}\prod _{v\in V}P(v)} or equivalently, to maximize the expected log probability of a training sample v {\displaystyle v} selected randomly from V {\displaystyle V} : arg ⁡ max W E [ log ⁡ P ( v ) ] {\displaystyle \arg \max _{W}\mathbb {E} \left[\log P(v)\right]} The algorithm most often used to train RBMs, that is, to optimize the weight matrix W {\displaystyle W} , is the contrastive divergence (CD) algorithm due to Hinton, originally developed to train PoE (product of experts) models. The algorithm performs Gibbs sampling and is used inside a gradient descent procedure (similar to the way backpropagation is used inside such a procedure when training feedforward neural nets) to compute weight update. The basic, single-step contrastive divergence (CD-1) procedure for a single sample can be summarized as follows: Take a training sample v, compute the probabilities of the hidden units and sample a hidden activation vector h from this probability distribution. Compute the outer product of v and h and call this the positive gradient. From h, sample a reconstruction v' of the visible units, then resample the hidden activations h' from this. (Gibbs sampling step) Compute the outer product of v' and h' and call this the negative gradient. Let the update to the weight matrix W {\displaystyle W} be the positive gradient minus the negative gradient, times some learning rate: Δ W = ϵ ( v h T − v ′ h ′ T ) {\displaystyle \Delta W=\epsilon (vh^{\mathsf {T}}-v'h'^{\mathsf {T}})} . Update the biases a and b analogously: Δ a = ϵ ( v − v ′ ) {\displaystyle \Delta a=\epsilon (v-v')} , Δ b = ϵ ( h − h ′ ) {\displaystyle \Delta b=\epsilon (h-h')} . A Practical Guide to Training RBMs written by Hinton can be found on his homepage. == Stacked Restricted Boltzmann Machine == The difference between the Stacked Restricted Boltzmann Machines and RBM is that RBM has lateral connections within a layer that are prohibited to make analysis tractable. On the other hand, the Stacked Boltzmann consists of a combination of an unsupervised three-layer network with symmetric weights and a supervised fine-tuned top layer for recognizing three classes. The usage of Stacked Boltzmann is to understand Natural languages, retrieve documents, image generation, and classification. These functions are trained with unsupervised pre-training and/or supervised fine-tuning. Unlike the undirected symmetric top layer, with a two-way unsymmetric layer for connection for RBM. The restricted Boltzmann's connection is three-layers with asymmetric weights, and two networks are combined into one. Stacked Boltzmann does share similarities with RBM, the neuron for Stacked Boltzmann is a stochastic binary Hopfield neuron, which is the same as the Restricted Boltzmann Machine. The energy from both Restricted Boltzmann and RBM is given by Gibb's probability measure: E = − 1 2 ∑ i , j w i j s i s j + ∑ i θ i s i {\displaystyle E=-{\frac {1}{2}}\sum _{i,j}{w_{ij}{s_{i}}{s_{j}}}+\sum _{i}{\theta _{i}}{s_{i}}} . The training process of Restricted Boltzmann is similar to RBM. Restricted Boltzmann train one layer at a time and approximate equilibrium state with a 3-segment pass, not performing back propagation. Restricted Boltzmann uses both supervised and unsupervised on different RBM for pre-training for classification and recognition. The training uses contrastive divergence with

    Read more →
  • Eric Brill

    Eric Brill

    Eric Brill is a computer scientist specializing in natural language processing. He created the Brill tagger, a supervised part of speech tagger. Another research paper of Brill introduced a machine learning technique now known as transformation-based learning. == Biography == Brill earned a BA in mathematics from the University of Chicago in 1987 and a MS in Computer Science from UT Austin in 1989. In 1994, he completed his PhD at the University of Pennsylvania. He was an assistant professor at Johns Hopkins University from 1994 to 1999. In 1999, he left JHU for Microsoft Research, he developed a system called "Ask MSR" that answered search engine queries written as questions in English, and was quoted in 2004 as predicting the shift of Google's web-page based search to information based search. In 2009 he moved to eBay to head their research laboratories.

    Read more →
  • Outline of brain mapping

    Outline of brain mapping

    The following outline is provided as an overview of and topical guide to brain mapping: Brain mapping – set of neuroscience techniques predicated on the mapping of (biological) quantities or properties onto spatial representations of the (human or non-human) brain resulting in maps. Brain mapping is further defined as the study of the anatomy and function of the brain and spinal cord through the use of imaging (including intra-operative, microscopic, endoscopic and multi-modality imaging), immunohistochemistry, molecular and optogenetics, stem cell and cellular biology, engineering (material, electrical and biomedical), neurophysiology and nanotechnology. == Broad scope == History of neuroscience History of neurology Brain mapping Human brain Neuroscience Nervous system. === The neuron doctrine === Neuron doctrine – A set of carefully constructed elementary set of observations regarding neurons. For more granularity, more current, and more advanced topics, see the cellular level section Asserts that neurons fall under the broader cell theory, which postulates: All living organisms are composed of one or more cells. The cell is the basic unit of structure, function, and organization in all organisms. All cells come from preexisting, living cells. The Neuron doctrine postulates several elementary aspects of neurons: The brain is made up of individual cells (neurons) that contain specialized features such as dendrites, a cell body, and an axon. Neurons are cells differentiable from other tissues in the body. Neurons differ in size, shape, and structure according to their location or functional specialization. Every neuron has a nucleus, which is the trophic center of the cell (The part which must have access to nutrition). If the cell is divided, only the portion containing the nucleus will survive. Nerve fibers are the result of cell processes and the outgrowths of nerve cells. (Several axons are bound together to form one nerve fibril. See also: Neurofilament. Several nerve fibrils then form one large nerve fiber. Myelin, an electrical insulator, forms around selected axons. Neurons are generated by cell division. Neurons are connected by sites of contact and not via cytoplasmic continuity. (A cell membrane isolates the inside of the cell from its environment. Neurons do not communicate via direct cytoplasm to cytoplasm contact.) Law of dynamic polarization. Although the axon can conduct in both directions, in tissue there is a preferred direction of transmission from cell to cell. Elements added later to the initial Neuron doctrine A barrier to transmission exists at the site of contact between two neurons that may permit transmission. (Synapse) Unity of transmission. If a contact is made between two cells, then that contact can be either excitatory or inhibitory, but will always be of the same type. Dale's law, each nerve terminal releases a single type of neurotransmitter. Some of the basic postulates in the Neuron doctrine have been subsequently questioned, refuted, or updated. See the cellular level section topics for additional information. === Map, atlas, and database projects === Brain Activity Map Project – 2013 NIH $3 billion project to map every neuron in the human brain in ten years, based upon the Human Genome Project. NIH Brain Research through Advancing Innovative Neurotechnologies (BRAIN) Initiative [1] Community outreach site for above where the public may comment [2] Human Brain Project (EU) – 1 billion euro, 10-year project to simulate the human brain with supercomputers. BigBrain A high-resolution 3D atlas of the human brain created as part of the HBP. Human Connectome Project – 2009 NIH $30 million project to build a network map of the human brain, including structural (anatomical) and functional elements. Emphasis included research into dyslexia, autism, Alzheimer's disease, and schizophrenia. See also Connectome a, comprehensive map of neural connections in the brain. Allen Brain Atlas – 2003 $100 million project funded by Paul Allen (Microsoft) BrainMaps – National Institute of Health (NIH) database including 60 terabytes of image scans of primate and non-primates, integrated with information covering structure and function. NeuroNames – Defines the brain in terms of about 550 primary structures (about 850 unique structures) to which all other structures, names, and synonyms are related. About 15,000 neuroanatomical terms are cross indexed, including many synonyms in seven languages. Coverage includes the brain and spinal cord of the four species most frequently studied by neuroscientists: human, macaque (monkey), rat and mouse. The controlled, standardized vocabulary for each structure is located in an unambiguous, strict physical hierarchy, and these terms are selected based on ease of pronunciation, mnemonic value, and frequency of use in recent neuroscientific publications. Relation of each structure to its superstructures and substructures is included. The controlled vocabulary is suitable for uniquely indexing neuroanatomical information in digital databases. Decade of the Brain 1990–1999 promotion by NIH and the Library of Congress "to enhance public awareness of the benefits to be derived from brain research". Communications targeted Members of Congress, staffs, and the general public to promote funding. Talairach Atlas see Jean Talairach Harvard Whole Brain Atlas see Human brain MNI Template see Medical image computing Blue Brain Project and Artificial brain International Consortium for Brain Mapping see Brain Mapping List of neuroscience databases NIH Toolbox National Institute of Health (USA) toolbox for the assessment of neurological and behavioral function Organization for Human Brain Mapping The Organization for Human Brain Mapping (OHBM) is an international society dedicated to using neuroimaging to discover the organization of the human brain. == Imaging and recording systems == This section covers imaging and recording systems. The general section covers history, neuroimaging, and techniques for mapping specific neural connections. The specific systems section covers the various specific technologies, including experimental and widely deployed imaging and recording systems. === General === Most imaging work to date on individual neurons has been conducted outside the brain, typically on large neurons, and has been most frequently destructive. New techniques are however rapidly emerging. Search on "Single neuron imaging" and see related topics: Biological neuron model, Single-unit recording, Neural oscillation, Computational neuroscience. dMRI (above) is also promising in non-destructive imaging of single neurons inside the brain. History of neuroimaging (redirects from Brain scanner) Neuroimaging (redirects from Brain function map) Connectomics – mapping technique showing neural connections in a nervous system. === Specific systems === Cortical stimulation mapping Diffusion MRI (dMRI) – includes diffusion tensor imaging (DTI) and diffusion functional MRI (DfMRI). dMRI is a recent breakthrough in brain mapping allowing the visualization of cross connections between different anatomical parts of the brain. It allows noninvasive imaging of white matter fiber structure and in addition to mapping can be useful in clinical observations of abnormalities, including damage from stroke. Electroencephalography (EEG) – uses electrodes on the scalp and other techniques to detect the electrical flow of currents. Electrocorticography – intracranial EEG, the practice of using electrodes placed directly on the exposed surface of the brain to record electrical activity from the cerebral cortex. Electrophysiological techniques for clinical diagnosis Functional magnetic resonance imaging (fMRI) Medical image computing (brain research of leads medical and surgical uses of mapping technology) Neurostimulation (in research stimulation is frequently used in conjunction with imaging) Positron emission tomography (PET) – a nuclear medical imaging technique that produces a three-dimensional image or picture of functional processes in the body. The system detects pairs of gamma rays emitted indirectly by a positron-emitting radionuclide (tracer), which is introduced into the body on a biologically active molecule. Three-dimensional images of tracer concentration within the body are then constructed by computer analysis. In modern scanners, three dimensional imaging is often accomplished with the aid of a CT X-ray scan performed on the patient during the same session, in the same machine. === Imaging and recording componentry === ==== Electrochemical ==== Haemodynamic response – the rapid delivery of blood to active neuronal tissues. Blood Oxygenation Level Dependent signal (BOLD), corresponds to the concentration of deoxyhemoglobin. The BOLD effect is based on the fact that when neuronal activity is increased in one part of the brain, there is also an increased amount of cerebral blood flow to that area. Functional m

    Read more →
  • Language model

    Language model

    A language model is a computational model that predicts sequences in natural language. Language models are useful for a variety of tasks, including speech recognition, machine translation, natural language generation (generating more human-like text), optical character recognition, route optimization, handwriting recognition, grammar induction, information retrieval and disaster response. Large language models (LLMs), currently their most advanced form as of 2026, are predominantly based on transformers trained on larger datasets (frequently using texts scraped from the public internet). They have superseded recurrent neural network-based models, which had previously superseded the purely statistical models, such as the word n-gram language model. == History == Noam Chomsky did pioneering work on language models in the 1950s by developing a theory of formal grammars. In 1980, statistical approaches were explored and found to be more useful for many purposes than rule-based formal grammars. Discrete representations like word n-gram language models, with probabilities for discrete combinations of words, made significant advances. In the 2000s, continuous representations for words, such as word embeddings, began to replace discrete representations. Typically, the representation is a real-valued vector that encodes a word’s meaning such that words closer in vector space are similar in meaning and common relationships between words, such as plurality or gender, are preserved. == Pure statistical models == In 1980, the first significant statistical language model was proposed, and during the decade IBM performed 'Shannon-style' experiments, in which potential sources for language modeling improvement were identified by observing and analyzing the performance of human subjects in predicting or correcting text. === Models based on word n-grams === === Exponential === Maximum entropy language models encode the relationship between a word and the n-gram history using feature functions. The equation is P ( w m ∣ w 1 , … , w m − 1 ) = 1 Z ( w 1 , … , w m − 1 ) exp ⁡ ( a T f ( w 1 , … , w m ) ) {\displaystyle P(w_{m}\mid w_{1},\ldots ,w_{m-1})={\frac {1}{Z(w_{1},\ldots ,w_{m-1})}}\exp(a^{T}f(w_{1},\ldots ,w_{m}))} where Z ( w 1 , … , w m − 1 ) {\displaystyle Z(w_{1},\ldots ,w_{m-1})} is the partition function, a {\displaystyle a} is the parameter vector, and f ( w 1 , … , w m ) {\displaystyle f(w_{1},\ldots ,w_{m})} is the feature function. In the simplest case, the feature function is just an indicator of the presence of a certain n-gram. It is helpful to use a prior on a {\displaystyle a} or some form of regularization. The log-bilinear model is another example of an exponential language model. === Skip-gram model === == Neural models == === Recurrent neural network === Continuous representations or embeddings of words are produced in recurrent neural network-based language models (known also as continuous space language models). Such continuous space embeddings help to alleviate the curse of dimensionality, which is the consequence of the number of possible sequences of words increasing exponentially with the size of the vocabulary, further causing a data sparsity problem. Neural networks avoid this problem by representing words as non-linear combinations of weights in a neural net. === Large language models === Although sometimes matching human performance, it is not clear whether they are plausible cognitive models. At least for recurrent neural networks, it has been shown that they sometimes learn patterns that humans do not, but fail to learn patterns that humans typically do. == Evaluation and benchmarks == Evaluation of the quality of language models is mostly done by comparison to human created sample benchmarks created from typical language-oriented tasks. Other, less established, quality tests examine the intrinsic character of a language model or compare two such models. Since language models are typically intended to be dynamic and to learn from data they see, some proposed models investigate the rate of learning, e.g., through inspection of learning curves. Various data sets have been developed for use in evaluating language processing systems. These include: Massive Multitask Language Understanding (MMLU) Corpus of Linguistic Acceptability GLUE benchmark Microsoft Research Paraphrase Corpus Multi-Genre Natural Language Inference Question Natural Language Inference Quora Question Pairs Recognizing Textual Entailment Semantic Textual Similarity Benchmark SQuAD question answering Test Stanford Sentiment Treebank Winograd NLI BoolQ, PIQA, SIQA, HellaSwag, WinoGrande, ARC, OpenBookQA, NaturalQuestions, TriviaQA, RACE, BIG-bench hard, GSM8k, RealToxicityPrompts, WinoGender, CrowS-Pairs

    Read more →
  • Diane Litman

    Diane Litman

    Diane Litman is an American professor of computer science at the University of Pittsburgh. She also jointly holds the positions of senior scientist with the Learning Research and Development Center and faculty with the Intelligent Systems department. Litman is noted for her work in the areas of artificial intelligence, computational linguistics, knowledge representation and reasoning, natural language processing, and user modeling. == Education == Litman did her undergraduate studies at the College of William and Mary and her master's and PhD degrees at the University of Rochester. == Career == Before joining the University of Pittsburgh, she was an assistant professor at Columbia University. She additionally held the position of a research scientist in the Artificial Intelligence Principles Research Department Laboratory at AT&T Labs. Litman has held the position of Chair of the North American Chapter of the Association for Computational Linguistics two times, elected twice for the position, whose tenure lasts four years. She is also a distinguished member of the executive committee of the Association for Computational Linguistics, and a member of the editorial boards of Computational Linguistics and User Modeling and User-Adapted Interaction. She has also held the position of Leverhulme Professor at the University of Edinburgh. Litman was the keynote speaker at the Speech and Language Technology in Education 2013 symposium, the 2006 SIGdial Meeting on Discourse and Dialogue, and at the 2008 Symposium of the Annual Meeting of the Society for the Study of Artificial Intelligence and Simulation of Behaviour. She also sits on the board of the several interest groups, including the International Speech Communication Association's Special Interest Group on Speech and Language Technology in Education. Litman has served as chair, organizer, and a senior member of numerous committees of peer-reviewed scientific journals. == Awards and recognition == She has also co-authored numerous award-winning papers and was awarded senior member status by the Association for the Advancement of Artificial Intelligence in 2011, an award designed to honor those who have "achieved significant accomplishments within the field of artificial intelligence."

    Read more →