Explore the best AI Writing Tools — independent reviews, comparisons, pricing and step-by-step how-to guides, curated by Aizhi.
openPipeline is an open-source plug-in for Autodesk Maya that is designed to assist in a Production Pipeline structure and Computer animation. == Development == Created in Maya Embedded Language, openPipeline was initiated at Eyebeam Atelier and further developed at Pratt Institute in the Digital Arts Lab. The initial release date was December 28, 2006. == Contributors == Rob O'Neill (Creator) Paris Mavroidis Meng-Han Ho
Read more →
In automata theory, a Muller automaton is a type of an ω-automaton. The acceptance condition separates a Muller automaton from other ω-automata. The Muller automaton is defined using a Muller acceptance condition, i.e. the set of all states visited infinitely often must be an element of the acceptance set. Both deterministic and non-deterministic Muller automata recognize the ω-regular languages. They are named after David E. Muller, an American mathematician and computer scientist, who invented them in 1963. == Formal definition == Formally, a deterministic Muller-automaton is a tuple A = (Q,Σ,δ,q0,F) that consists of the following information: Q is a finite set. The elements of Q are called the states of A. Σ is a finite set called the alphabet of A. δ: Q × Σ → Q is a function, called the transition function of A. q0 is an element of Q, called the initial state. F is a set of sets of states. Formally, F ⊆ P(Q) where P(Q) is powerset of Q. F defines the acceptance condition. A accepts exactly those runs in which the set of infinitely often occurring states is an element of F In a non-deterministic Muller automaton, the transition function δ is replaced with a transition relation Δ that returns a set of states and the initial state q0 is replaced by a set of initial states Q0. Generally, 'Muller automaton' refers to a non-deterministic Muller automaton. For more comprehensive formalisation look at ω-automaton. == Equivalence with other ω-automata == The Muller automata are equally expressive as parity automata, Rabin automata, Streett automata, and non-deterministic Büchi automata, to mention some, and strictly more expressive than the deterministic Büchi automata. The equivalence of the above automata and non-deterministic Muller automata can be shown very easily as the accepting conditions of these automata can be emulated using the acceptance condition of Muller automata and vice versa. McNaughton's theorem demonstrates the equivalence of non-deterministic Büchi automaton and deterministic Muller automaton. Thus, deterministic and non-deterministic Muller automata are equivalent in terms of the languages they can accept. == Transformation to non-deterministic Muller automata == Following is a list of automata constructions that each transforms a type of ω-automata to a non-deterministic Muller automaton. From Büchi automata If B is the set of final states in a Büchi automaton with the set of states Q, we can construct a Muller automaton with same set of states, transition function and initial state with the Muller accepting condition as F = { X | X ∈ P(Q) ∧ X ∩ B ≠ ∅}. From Rabin automata/parity automata Similarly, the Rabin conditions ( E j , F j ) {\displaystyle (E_{j},F_{j})} can be emulated by constructing the acceptance set in the Muller automaton as all sets F ⊆ Q {\displaystyle F\subseteq Q} that satisfy F ∩ E j = ∅ {\displaystyle F\cap E_{j}=\emptyset } and F ∩ F j ≠ ∅ {\displaystyle F\cap F_{j}\neq \emptyset } , for some j. Note that this covers the case of parity automata too, as the parity acceptance condition can be expressed as a Rabin acceptance condition easily. From Streett automata The Streett conditions ( E j , F j ) {\displaystyle (E_{j},F_{j})} can be emulated by constructing the acceptance set in the Muller automaton as all sets F ⊆ Q {\displaystyle F\subseteq Q} that satisfy F ∩ F j = ∅ ⟹ F ∩ E j = ∅ {\displaystyle F\cap F_{j}=\emptyset \implies F\cap E_{j}=\emptyset } , for all j. == Transformation to deterministic Muller automata == From Büchi automaton McNaughton's theorem provides a procedure to transform any non-deterministic Büchi automaton into a deterministic Muller automaton.
Read more →
Intelligent character recognition (ICR) is a method of extracting handwritten text from images. It is a more sophisticated type of OCR technology that recognizes different handwriting styles and fonts to intelligently interpret data from physical documents. ICR is used to organize paper-based unstructured data by scanning documents, extracting information, and adapting extracted data for database storage. ICR algorithms collaborate with OCR to automate data entry from forms by removing the need for keystrokes. It has a high degree of accuracy and is a dependable method for processing various handwritten media quickly. == Capabilities == Most ICR software has a self-learning neural network-based algorithms, which automatically update the recognition database for new handwriting patterns. It extends the usefulness of scanning devices for the purpose of document processing, from printed character recognition (a function of OCR) to hand-written matter recognition. Because this process is involved in recognizing hand writing, accuracy levels may, in some circumstances, not be very good but can achieve 97%+ accuracy rates in reading handwriting in structured forms. Often to achieve these high recognition rates several read engines are used within the software and each is given elective voting rights to determine the true reading of characters. In numeric fields, engines which are designed to read numbers take preference, while in alpha fields, engines designed to read hand written letters have higher elective rights. When used in conjunction with a bespoke interface hub, hand-written data can be automatically populated into a back office system avoiding laborious manual keying and can be more accurate than traditional human data entry. === Automated forms processing === An important development of ICR was the invention of automated forms processing in 1993 by Joseph Corcoran who was awarded a patent on the invention. This involved a three-stage process of capturing the image of the form to be processed by ICR and preparing it to enable the ICR engine to give best results, then capturing the information using the ICR engine and finally processing the results to automatically validate the output from the ICR engine. This application of ICR increased the usefulness of the technology and made it applicable for use with real world forms in normal business applications. Modern software applications use ICR as a technology of recognizing text in forms filled in by hand (hand-printed). == Differences between ICR and OCR == === OCR === Optical character recognition (OCR) is commonly considered to apply to any recognition technique that reads machine printed text. An example of a traditional OCR use case would be to translate the characters from an image of a printed document, such as a book page, newspaper clipping, or legal contract, into a separate file that could be searched and updated with a word processor or document viewer. It's also quite helpful for automating the processing of forms. Information can be swiftly extracted from form fields and entered into another application, like a spreadsheet or database, by zonally applying the OCR engine to those fields. Yet, data is typically manually input rather than typed into form fields. Character identification becomes even more challenging while reading handwritten material. The diversity of more than 700,000 printed font variants is tiny compared to the near unlimited variations in hand-printed characters. The recognition program must take into account not just stylistic differences but also the kind of writing implement used, the standard of the paper, errors, hand stability, and smudges or running ink. === ICR === Intelligent character recognition (ICR) makes use of continuously improving algorithms to collect more information about the variances in hand-printed characters and more precisely identify them. ICR, which was created in the early 1990s to aid in the automation of forms processing, enables the conversion of manually entered data into text that is simple to read, search for, and change. When used to read characters that are obviously divided into distinct areas or zones, such as fixed fields seen on many structured forms, it works best. Both OCR and ICR can be configured to read a variety of languages; however, limiting the expected character set to a smaller number of languages will produce better recognition outcomes. ICR cannot read cursive handwriting since it must still be able to assess each character individually. While writing in cursive, it might be difficult to tell where one character ends and another one begins, and there are more differences across samples than when hand-printing text. A more recent method called intelligent word recognition (IWR) focuses on reading a word in context rather than recognizing individual characters. == Intelligent word recognition == Intelligent word recognition (IWR) can recognize and extract not only printed-handwritten information, cursive handwriting as well. ICR recognizes on the character-level, whereas IWR works with full words or phrases. Capable of capturing unstructured information from every day pages, IWR is said to be more evolved than hand print ICR. Not meant to replace conventional ICR and OCR systems, IWR is optimized for processing real-world documents that contain mostly free-form, hard-to-recognize data fields that are inherently unsuitable for ICR. This means that the highest and best use of IWR is to eliminate a high percentage of the manual entry of handwritten data and run-on hand print fields on documents that otherwise could be keyed only by humans.
Read more →
Peter Gerstoft is a Danish-American scientist and engineer specializing in ocean acoustics, seismology, and signal processing. He is currently a professor in the Department of Electrical and Photonics Engineering at the Technical University of Denmark. He was previously a Distinguished Data Scientist at the Scripps Institution of Oceanography at the University of California, San Diego and an adjunct professor in the Department of Electrical and Computer Engineering at UC San Diego. == Education == Gerstoft received his MSc in engineering from the Technical University of Denmark in 1983 and another MSc from the University of Western Ontario in 1984. He completed his PhD in engineering at the Technical University of Denmark in 1986. == Career == Gerstoft began his career in acoustics and vibrations at Odegaard & Danneskiold-Samsøe (1987–1992). He then served as a Senior Scientist at the NATO SACLANT Undersea Research Centre in La Spezia, Italy, from 1992 to 1997. Between 1999 and 2000, Gerstoft worked as a Senior Seismic Acoustic Officer with the Comprehensive Nuclear-Test-Ban Treaty Organization. He has been a Data Scientist at the Scripps Institution of Oceanography since 1997. From 2013, he held an adjunct faculty position in Electrical and Computer Engineering at UC San Diego, where he taught courses on seismology, data assimilation, and machine learning for physical systems. Gerstoft retired from UC San Diego in 2025 and accepted an appointment as Professor of Electrical and Photonics Engineering at the Technical University of Denmark in 2026 . == Research and contributions == Gerstoft's research focuses on environmental signal processing, with a particular emphasis on inversion methods, including their theoretical development, algorithmic implementation, and practical applications. In the 1990s, he investigated the use of nonlinear optimization and Bayesian approaches in acoustic inverse problems related to source localization and environmental parameter estimation. His work integrated physical propagation models with Bayesian sampling methods and a range of likelihood functions. These techniques have been applied to various data types, including vertical sensor arrays, single-sensor broadband data, and transmission loss measurements, and contributed to a general framework for inversion based on Gaussian assumptions. He has also conducted research in machine learning and sparse signal processing, particularly in the context of sensor array data. This includes applications such as direction of arrival estimation and source localization, including for seismic events such as the 2011 Tōhoku earthquake and for ship tracking in ocean environments. His work on sparse Bayesian sequential methods and techniques for estimating Lagrange multipliers in constrained optimization problems has contributed to the development of adaptive and high-resolution signal processing techniques. Gerstoft has applied supervised learning and deep neural networks to problems in physical acoustics, including source localization in ocean waveguides. He has also co-authored several review articles on the use of machine learning in acoustics and seismology. == Honors == Fulbright Scholar, Massachusetts Institute of Technology (1989–1990) Fellow, Acoustical Society of America (2003) Member, American Geophysical Union (since 2004) Senior Member, Institute of Electrical and Electronics Engineers (2018) Fellow, Institute of Electrical and Electronics Engineers (2023) == Selected publications == === Book === Diachok, O., Caiti, A., Gerstoft, P., & Schmidt, H. (Eds.). Full Field Inversion Methods in Ocean and Seismo-Acoustics. Kluwer Academic Publishers, 1995. === Selected articles === Gerstoft, P. (1994). "Inversion of seismo-acoustic data using genetic algorithms and a posteriori probability distributions". Journal of the Acoustical Society of America. 95 (2): 770–782. doi:10.1121/1.408467. Gerstoft, P., & Mecklenbrauker, C. F. (1998). "Ocean acoustic inversion with estimation of a posteriori probability distributions". Journal of the Acoustical Society of America. 104 (2): 808–819. doi:10.1121/1.423287. Sabra, K. G., Gerstoft, P., Roux, P., Kuperman, W. A., & Fehler, M. (2005). "Extracting time-domain Green's function estimates from ambient seismic noise". Geophysical Research Letters. 32, L03310. Xenaki, A., Gerstoft, P., & Mosegaard, K. (2014). "Compressive beamforming". Journal of the Acoustical Society of America. 136, 260–271. Niu, H., Reeves, D., & Gerstoft, P. (2017). "Source localization in an ocean waveguide using supervised machine learning". Journal of the Acoustical Society of America. 142, 1176–1188.
Read more →
In machine learning (ML), a learning curve (or training curve) is a graphical representation that shows how a model's performance on a training set (and usually a validation set) changes with the number of training iterations (epochs) or the amount of training data. Typically, the number of training epochs or training set size is plotted on the x-axis, and the value of the loss function (and possibly some other metric such as the cross-validation score) on the y-axis. Synonyms include error curve, experience curve, improvement curve and generalization curve. More abstractly, learning curves plot the difference between learning effort and predictive performance, where "learning effort" usually means the number of training samples, and "predictive performance" means accuracy on testing samples. Learning curves have many useful purposes in ML, including: choosing model parameters during design, adjusting optimization to improve convergence, and diagnosing problems such as overfitting (or underfitting). Learning curves can also be tools for determining how much a model benefits from adding more training data, and whether the model suffers more from a variance error or a bias error. If both the validation score and the training score converge to a certain value, then the model will no longer significantly benefit from more training data. == Formal definition == When creating a function to approximate the distribution of some data, it is necessary to define a loss function L ( f θ ( X ) , Y ) {\displaystyle L(f_{\theta }(X),Y)} to measure how good the model output is (e.g., accuracy for classification tasks or mean squared error for regression). We then define an optimization process which finds model parameters θ {\displaystyle \theta } such that L ( f θ ( X ) , Y ) {\displaystyle L(f_{\theta }(X),Y)} is minimized, referred to as θ ∗ {\displaystyle \theta ^{}} . === Training curve for amount of data === If the training data is { x 1 , x 2 , … , x n } , { y 1 , y 2 , … y n } {\displaystyle \{x_{1},x_{2},\dots ,x_{n}\},\{y_{1},y_{2},\dots y_{n}\}} and the validation data is { x 1 ′ , x 2 ′ , … x m ′ } , { y 1 ′ , y 2 ′ , … y m ′ } {\displaystyle \{x_{1}',x_{2}',\dots x_{m}'\},\{y_{1}',y_{2}',\dots y_{m}'\}} , a learning curve is the plot of the two curves i ↦ L ( f θ ∗ ( X i , Y i ) ( X i ) , Y i ) {\displaystyle i\mapsto L(f_{\theta ^{}(X_{i},Y_{i})}(X_{i}),Y_{i})} i ↦ L ( f θ ∗ ( X i , Y i ) ( X i ′ ) , Y i ′ ) {\displaystyle i\mapsto L(f_{\theta ^{}(X_{i},Y_{i})}(X_{i}'),Y_{i}')} where X i = { x 1 , x 2 , … x i } {\displaystyle X_{i}=\{x_{1},x_{2},\dots x_{i}\}} === Training curve for number of iterations === Many optimization algorithms are iterative, repeating the same step (such as backpropagation) until the process converges to an optimal value. Gradient descent is one such algorithm. If θ i ∗ {\displaystyle \theta _{i}^{}} is the approximation of the optimal θ {\displaystyle \theta } after i {\displaystyle i} steps, a learning curve is the plot of i ↦ L ( f θ i ∗ ( X , Y ) ( X ) , Y ) {\displaystyle i\mapsto L(f_{\theta _{i}^{}(X,Y)}(X),Y)} i ↦ L ( f θ i ∗ ( X , Y ) ( X ′ ) , Y ′ ) {\displaystyle i\mapsto L(f_{\theta _{i}^{}(X,Y)}(X'),Y')}
Read more →
Curious about the best AI marketing tool? An AI marketing tool is software that uses machine learning to help you get more done — it combines speed, accuracy, and an interface that just works. Hands-on testing shows real-world results vary, so a short free trial is the smartest way to decide. Whether you are a beginner or a pro, the right AI marketing tool slots into your workflow and pays for itself fast. This guide breaks down the top picks, their pros and cons, and who each one is best for.
Read more →
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 →
Curious about the best AI video generator? An AI video generator is software that uses machine learning to help you get more done — it combines speed, accuracy, and an interface that just works. Hands-on testing shows real-world results vary, so a short free trial is the smartest way to decide. Whether you are a beginner or a pro, the right AI video generator slots into your workflow and pays for itself fast. This guide breaks down the top picks, their pros and cons, and who each one is best for.
Read more →
TigerGraph is a private company headquartered in Redwood City, California. It provides graph database and graph analytics software. == History == TigerGraph was founded in 2012 by programmer Yu, Ruoming, Li, Like and Mingxi, under the name GraphSQL. In September 2017, the company came out of stealth mode under the name TigerGraph with $33 million in funding. It raised an additional $32 million in funding in September 2019 and another $105 million in a series C round in February 2021. Cumulative funding as of March 2021 is $170 million. == Products == TigerGraph's hybrid transactional/analytical processing database and analytics software can scale to hundreds of terabytes of data with trillions of edges, and is used for data intensive applications such as fraud detection, customer data analysis (customer 360), IoT, artificial intelligence and machine learning. It is available using the cloud computing delivery model. The analytics uses C++ based software and a parallel processing engine to process algorithms and queries. It has its own graph query language that is similar to SQL. TigerGraph also provides a software development kit for creating graphs and visual representations. As of Mar 2024, TigerGraph version is up to version 4.2.0 TigerGraph offers free Community Edition for developers, researchers, and educators. It can be obtained from https://dl.tigergraph.com/ == Query Language == GSQL , designed by Mingxi Wu and Alin Deutsch in 2015, is a SQL-like Turing complete query language. GSQL includes additions to make it compliant with the Graph Query Language standard.
Read more →
In dual decomposition a problem is broken into smaller subproblems and a solution to the relaxed problem is found. This method can be employed for MRF optimization. Dual decomposition is applied to markov logic programs as an inference technique. == Background == Discrete MRF Optimization (inference) is very important in Machine Learning and Computer vision, which is realized on CUDA graphical processing units. Consider a graph G = ( V , E ) {\displaystyle G=(V,E)} with nodes V {\displaystyle V} and Edges E {\displaystyle E} . The goal is to assign a label l p {\displaystyle l_{p}} to each p ∈ V {\displaystyle p\in V} so that the MRF Energy is minimized: (1) min Σ p ∈ V θ p ( l p ) + Σ p q ∈ ε θ p q ( l p ) ( l q ) {\displaystyle \min \Sigma _{p\in V}\theta _{p}(l_{p})+\Sigma _{pq\in \varepsilon }\theta _{pq}(l_{p})(l_{q})} Major MRF Optimization methods are based on Graph cuts or Message passing. They rely on the following integer linear programming formulation (2) min x E ( θ , x ) = θ . x = ∑ p ∈ V θ p . x p + ∑ p q ∈ ε θ p q . x p q {\displaystyle \min _{x}E(\theta ,x)=\theta .x=\sum _{p\in V}\theta _{p}.x_{p}+\sum _{pq\in \varepsilon }\theta _{pq}.x_{pq}} In many applications, the MRF-variables are {0,1}-variables that satisfy: x p ( l ) = 1 {\displaystyle x_{p}(l)=1} ⇔ {\displaystyle \Leftrightarrow } label l {\displaystyle l} is assigned to p {\displaystyle p} , while x p q ( l , l ′ ) = 1 {\displaystyle x_{pq}(l,l^{\prime })=1} , labels l , l ′ {\displaystyle l,l^{\prime }} are assigned to p , q {\displaystyle p,q} . == Dual Decomposition == The main idea behind decomposition is surprisingly simple: decompose your original complex problem into smaller solvable subproblems, extract a solution by cleverly combining the solutions from these subproblems. A sample problem to decompose: min x Σ i f i ( x ) {\displaystyle \min _{x}\Sigma _{i}f^{i}(x)} where x ∈ C {\displaystyle x\in C} In this problem, separately minimizing every single f i ( x ) {\displaystyle f^{i}(x)} over x {\displaystyle x} is easy; but minimizing their sum is a complex problem. So the problem needs to get decomposed using auxiliary variables { x i } {\displaystyle \{x^{i}\}} and the problem will be as follows: min { x i } , x Σ i f i ( x i ) {\displaystyle \min _{\{x^{i}\},x}\Sigma _{i}f^{i}(x^{i})} where x i ∈ C , x i = x {\displaystyle x^{i}\in C,x^{i}=x} Now we can relax the constraints by multipliers { λ i } {\displaystyle \{\lambda ^{i}\}} which gives us the following Lagrangian dual function: g ( { λ i } ) = min { x i ∈ C } , x Σ i f i ( x i ) + Σ i λ i . ( x i − x ) = min { x i ∈ C } , x Σ i [ f i ( x i ) + λ i . x i ] − ( Σ i λ i ) x {\displaystyle g(\{\lambda ^{i}\})=\min _{\{x^{i}\in C\},x}\Sigma _{i}f^{i}(x^{i})+\Sigma _{i}\lambda ^{i}.(x^{i}-x)=\min _{\{x^{i}\in C\},x}\Sigma _{i}[f^{i}(x^{i})+\lambda ^{i}.x^{i}]-(\Sigma _{i}\lambda ^{i})x} Now we eliminate x {\displaystyle x} from the dual function by minimizing over x {\displaystyle x} and dual function becomes: g ( { λ i } ) = min { x i ∈ C } Σ i [ f i ( x i ) + λ i . x i ] {\displaystyle g(\{\lambda ^{i}\})=\min _{\{x^{i}\in C\}}\Sigma _{i}[f^{i}(x^{i})+\lambda ^{i}.x^{i}]} We can set up a Lagrangian dual problem: (3) max { λ i } ∈ Λ g ( λ i ) = Σ i g i ( x i ) , {\displaystyle \max _{\{\lambda ^{i}\}\in \Lambda }g({\lambda ^{i}})=\Sigma _{i}g^{i}(x^{i}),} The Master problem (4) g i ( x i ) = m i n x i f i ( x i ) + λ i . x i {\displaystyle g^{i}(x^{i})=min_{x^{i}}f^{i}(x^{i})+\lambda ^{i}.x^{i}} where x i ∈ C {\displaystyle x^{i}\in C} The Slave problems == MRF optimization via Dual Decomposition == The original MRF optimization problem is NP-hard and we need to transform it into something easier. τ {\displaystyle \tau } is a set of sub-trees of graph G {\displaystyle G} where its trees cover all nodes and edges of the main graph. And MRFs defined for every tree T {\displaystyle T} in τ {\displaystyle \tau } will be smaller. The vector of MRF parameters is θ T {\displaystyle \theta ^{T}} and the vector of MRF variables is x T {\displaystyle x^{T}} , these two are just smaller in comparison with original MRF vectors θ , x {\displaystyle \theta ,x} . For all vectors θ T {\displaystyle \theta ^{T}} we'll have the following: (5) ∑ T ∈ τ ( p ) θ p T = θ p , ∑ T ∈ τ ( p q ) θ p q T = θ p q . {\displaystyle \sum _{T\in \tau (p)}\theta _{p}^{T}=\theta _{p},\sum _{T\in \tau (pq)}\theta _{pq}^{T}=\theta _{pq}.} Where τ ( p ) {\displaystyle \tau (p)} and τ ( p q ) {\displaystyle \tau (pq)} denote all trees of τ {\displaystyle \tau } than contain node p {\displaystyle p} and edge p q {\displaystyle pq} respectively. We simply can write: (6) E ( θ , x ) = ∑ T ∈ τ E ( θ T , x T ) {\displaystyle E(\theta ,x)=\sum _{T\in \tau }E(\theta ^{T},x^{T})} And our constraints will be: (7) x T ∈ χ T , x T = x | T , ∀ T ∈ τ {\displaystyle x^{T}\in \chi ^{T},x^{T}=x_{|T},\forall T\in \tau } Our original MRF problem will become: (8) min { x T } , x Σ T ∈ τ E ( θ T , x T ) {\displaystyle \min _{\{x^{T}\},x}\Sigma _{T\in \tau }E(\theta ^{T},x^{T})} where x T ∈ χ T , ∀ T ∈ τ {\displaystyle x^{T}\in \chi ^{T},\forall T\in \tau } and x T ∈ x | T , ∀ T ∈ τ {\displaystyle x^{T}\in x_{|T},\forall T\in \tau } And we'll have the dual problem we were seeking: (9) max { λ T } ∈ Λ g ( { λ T } ) = ∑ T ∈ τ g T ( λ T ) , {\displaystyle \max _{\{\lambda ^{T}\}\in \Lambda }g(\{\lambda ^{T}\})=\sum _{T\in \tau }g^{T}(\lambda ^{T}),} The Master problem where each function g T ( . ) {\displaystyle g^{T}(.)} is defined as: (10) g T ( λ T ) = min x T E ( θ T + λ T , x T ) {\displaystyle g^{T}(\lambda ^{T})=\min _{x^{T}}E(\theta ^{T}+\lambda ^{T},x^{T})} where x T ∈ χ T {\displaystyle x^{T}\in \chi ^{T}} The Slave problems == Theoretical Properties == Theorem 1. Lagrangian relaxation (9) is equivalent to the LP relaxation of (2). min { x T } , x { E ( x , θ ) | x p T = s p , x T ∈ CONVEXHULL ( χ T ) } {\displaystyle \min _{\{x^{T}\},x}\{E(x,\theta )|x_{p}^{T}=s_{p},x^{T}\in {\text{CONVEXHULL}}(\chi ^{T})\}} Theorem 2. If the sequence of multipliers { α t } {\displaystyle \{\alpha _{t}\}} satisfies α t ≥ 0 , lim t → ∞ α t = 0 , ∑ t = 0 ∞ α t = ∞ {\displaystyle \alpha _{t}\geq 0,\lim _{t\to \infty }\alpha _{t}=0,\sum _{t=0}^{\infty }\alpha _{t}=\infty } then the algorithm converges to the optimal solution of (9). Theorem 3. The distance of the current solution { θ T } {\displaystyle \{\theta ^{T}\}} to the optimal solution { θ ¯ T } {\displaystyle \{{\bar {\theta }}^{T}\}} , which decreases at every iteration. Theorem 4. Any solution obtained by the method satisfies the WTA (weak tree agreement) condition. Theorem 5. For binary MRFs with sub-modular energies, the method computes a globally optimal solution.
Read more →
Iterative Viterbi decoding is an algorithm that spots the subsequence S of an observation O = {o1, ..., on} having the highest average probability (i.e., probability scaled by the length of S) of being generated by a given hidden Markov model M with m states. The algorithm uses a modified Viterbi algorithm as an internal step. The scaled probability measure was first proposed by John S. Bridle. An early algorithm to solve this problem, sliding window, was proposed by Jay G. Wilpon et al., 1989, with constant cost T = mn2/2. A faster algorithm consists of an iteration of calls to the Viterbi algorithm, reestimating a filler score until convergence. == The algorithm == A basic (non-optimized) version, finding the sequence s with the smallest normalized distance from some subsequence of t is: // input is placed in observation s[1..n], template t[1..m], // and [[distance matrix]] d[1..n,1..m] // remaining elements in matrices are solely for internal computations (int, int, int) AverageSubmatchDistance(char s[0..(n+1)], char t[0..(m+1)], int d[1..n,0..(m+1)]) { // score, subsequence start, subsequence end declare int e, B, E t'[0] := t'[m+1] := s'[0] := s'[n+1] := 'e' e := random() do e' := e for i := 1 to n do d'[i,0] := d'[i,m+1] := e (e, B, E) := ViterbiDistance(s', t', d') e := e/(E-B+1) until (e == e') return (e, B, E) } The ViterbiDistance() procedure returns the tuple (e, B, E), i.e., the Viterbi score "e" for the match of t and the selected entry (B) and exit (E) points from it. "B" and "E" have to be recorded using a simple modification to Viterbi. A modification that can be applied to CYK tables, proposed by Antoine Rozenknop, consists in subtracting e from all elements of the initial matrix d.
Read more →
Looking for the best conversational AI platform? An conversational AI platform is software that uses machine learning to help you get more done — it can save you hours every week by automating repetitive work. Most options offer a generous free tier, with paid plans unlocking higher limits, faster processing, and team features. Whether you are a beginner or a pro, the right conversational AI platform slots into your workflow and pays for itself fast. Read on for hands-on impressions, pricing tiers, and the standout features that matter.
Read more →
Gemini Enterprise Agent Platform (formerly known as Vertex AI) is a managed machine learning (ML) and artificial intelligence (AI) platform developed by Google Cloud. It provides a unified environment for building, training, deploying, and scaling ML models and generative AI applications. The platform integrates tools for the full ML lifecycle, including data preparation, model training, evaluation, deployment, and monitoring, under a single API and user interface. Vertex AI was announced at Google I/O and released as a generally available product on May 18, 2021. At launch, Google described Vertex AI as unifying its AutoML offerings with its prior Cloud AI Platform capabilities, and as adding operational features intended to help teams move models from experimentation into production use. On April 22, 2026, Google announced Gemini Enterprise Agent Platform as the replacement evolution of Vertex AI. == History == Google Cloud announced the general availability of Vertex AI on May 18, 2021, at the Google I/O developer conference. The platform was designed to consolidate Google Cloud's previously separate ML offerings, including AutoML and the legacy AI Platform, into a single system. At launch, Google claimed that Vertex AI required roughly 80% fewer lines of code to train a model compared to competing platforms. In June 2023, Google made generative AI support in Vertex AI generally available, giving developers access to foundation models including PaLM 2, Imagen, and Codey through the platform's Model Garden and the newly launched Generative AI Studio. At the time of this launch, Model Garden included over 60 models from Google and its partners. In August 2023, at the Google Cloud Next conference, Google announced further updates to Vertex AI, including the addition of third-party models such as Claude 2 from Anthropic and Llama 2 from Meta to the Model Garden, as well as new tools called Vertex AI Extensions for connecting models to APIs for real-time data retrieval. At the same event, Vertex AI Search and Conversation were made generally available, providing enterprise search and chatbot capabilities powered by foundation models. In April 2024, at Google Cloud Next, the company introduced Vertex AI Agent Builder, a no-code tool for creating AI-powered conversational agents built on top of Gemini large language models. This brought together the existing Vertex AI Search and Conversation products with new developer tools for building generative AI experiences. == Features == === Model training === Vertex AI supports both AutoML, which enables code-free model training on tabular, image, text, or video data, and custom training, which gives users full control over the ML framework, training code, and hyperparameter tuning. The platform provides serverless training as well as dedicated training clusters with GPU and TPU accelerators. Vertex AI Vizier handles automatic hyperparameter tuning, and Vertex AI Experiments allows comparison and tracking of training runs. === Model Garden === The Vertex AI Model Garden is a curated catalog of over 200 enterprise-ready models, including Google's own foundation models (such as Gemini, Imagen, and Veo), third-party models (such as Anthropic's Claude and Mistral AI models), and popular open-source models (such as Llama and Gemma). Models are accessible as fully managed model-as-a-service APIs. === Pipelines (workflow orchestration) === Vertex AI Pipelines provides managed orchestration of ML workflows and supports pipelines built with the Kubeflow Pipelines SDK, among other options described in Google Cloud documentation. === Vertex AI Studio === Vertex AI Studio provides tools for prompt design, testing, and model management, allowing developers to prototype and build generative AI applications using natural language, code, images, or video. === Agent Builder and Agent Engine === Vertex AI Agent Builder is a suite of products for building, deploying, and governing AI agents in production environments. It supports development with the open-source Agent Development Kit (ADK) and other frameworks. Vertex AI Agent Engine provides the underlying infrastructure for deploying and scaling agents, with support for enterprise security features including HIPAA compliance, customer-managed encryption keys (CMEK), and VPC Service Controls. === Generative AI tooling and model access === Google markets Vertex AI as providing access to Google foundation models (including the Gemini family) and developer tools such as Vertex AI Studio, along with a model catalog that includes Google and selected open source models (marketed as "Model Garden"). Google has also offered products within Vertex AI aimed at building generative search and conversational applications, including offerings named "Vertex AI Search" and "Vertex AI Conversation" as reported in 2023 coverage of platform updates. === MLOps tools === The platform includes a range of MLOps capabilities: Vertex AI Pipelines for orchestrating and automating ML workflows as reusable pipelines. Vertex AI Feature Store for serving, sharing, and reusing ML features across projects. Vertex AI Model Registry for storing, versioning, and managing trained models. Vertex AI Model Monitoring for detecting training-serving skew and inference drift in deployed models. Vertex Explainable AI for interpreting model predictions. Vertex AI Workbench for managed JupyterLab notebook environments integrated with Google Cloud Storage and BigQuery. == Industry recognition == Google was named a Leader for the fifth consecutive year in the 2024 Gartner Magic Quadrant for Cloud AI Developer Services, a recognition that encompasses Vertex AI and its related offerings. Google was also recognized as a Leader in the 2024 Gartner Magic Quadrant for Data Science and Machine Learning Platforms and was named a Leader in the Forrester Wave for AI/ML Platforms, Q3 2024. In October 2025, Google was also named a Leader in the 2025 IDC (International Data Corporation) MarketScape for Worldwide GenAI Life-Cycle Foundation Model Software. == Pricing == Vertex AI uses a pay-as-you-go pricing model, with costs determined by the specific services consumed, including model training, prediction serving, and data storage. For generative AI tasks, pricing is based on a per-token model, with rates varying depending on the specific model used and whether tokens are input or output. Google offers a free tier for new users, which includes limited custom training hours and online prediction usage, along with an introductory US$300 in Google Cloud credits valid for 90 days. == Adoption == In the year following its 2021 launch, Google reported that usage of Vertex AI and BigQuery had driven 2.5 times more machine learning predictions compared to the prior year, and that active customers of Vertex AI Workbench had grown 25-fold over a six-month period. Early enterprise adopters included Ford, Wayfair, and Seagate, among others. Wayfair reported that it was able to run large model training jobs 5 to 10 times faster using the platform.
Read more →
Sinkov statistics, also known as log-weight statistics, is a specialized field of statistics that was developed by Abraham Sinkov, while working for the small Signal Intelligence Service organization, the primary mission of which was to compile codes and ciphers for use by the U.S. Army. The mathematics involved include modular arithmetic, a bit of number theory, some linear algebra of two dimensions with matrices, some combinatorics, and a little statistics. Sinkov did not explain the theoretical underpinnings of his statistics, or characterized its distribution, nor did he give a decision procedure for accepting or rejecting candidate plaintexts on the basis of their S1 scores. The situation becomes more difficult when comparing strings of different lengths because Sinkov does not explain how the distribution of his statistics changes with length, especially when applied to higher-order grams. As for how to accept or reject a candidate plaintext, Sinkov simply said to try all possibilities and to pick the one with the highest S1 value. Although the procedure works for some applications, it is inadequate for applications that require on-line decisions. Furthermore, it is desirable to have a meaningful interpretation of the S1 values.
Read more →
Robert Wilensky (26 March 1951 – 15 March 2013) was an American computer scientist and professor at the UC Berkeley School of Information, with his main focus of research in artificial intelligence. == Academic career == In 1971, Wilensky received his bachelor's degree in mathematics from Yale University, and in 1978, a Ph.D. in computer science from the same institution. After finishing his thesis, "Understanding Goal-Based Stories", Wilensky joined the faculty from the EECS Department of UC Berkeley. In 1986, he worked as the doctoral advisor of Peter Norvig, who then later published the standard textbook of the field: Artificial Intelligence: A Modern Approach. From 1993 to 1997, Wilensky was the Berkeley Computer Science Division Chair. During this time, he also served as director of the Berkeley Cognitive Science Program, director of the Berkeley Artificial Intelligence Research Project, and board member of the International Computer Science Institute. In 1997, he became a fellow of the Association for Computing Machinery "for research contributions to the areas of natural language processing and digital libraries as well as outstanding leadership in Computer Science." Furthermore, he also was a Fellow of the Association for the Advancement of Artificial Intelligence. He retired from faculty in 2007 and died on Friday, March 15, 2013, of a bacterial infection at the Alta Bates Summit Medical Center. Wilensky was married to Ann Danforth and he is survived by her and their two children, Avi and Eli Wilensky == Research == Throughout his career, Wilensky authored and co-authored over 60 scholarly articles and technical reports on AI, natural language processing, and information dissemination. In addition to his numerous technical publications, Wilensky also published two books on the programming language LISP, LISPcraft and Common LISPcraft, and had almost completed another book manuscript when he suffered a cardiac arrest and stopped writing. Among his publications are: R. Wilensky, (1986-09-17). Common LISPcraft. W. W. Norton & Company. ISBN 9780393955446. T. A. Phelps and R. Wilensky, "Toward active, extensible, networked documents: Multivalent architecture and applications," in Proc. 1st ACM Intl. Conf. on Digital Libraries, E. A. Fox and G. Marchionini, Eds., New York, NY: ACM Press, 1996, pp. 100–108. J. Traupman and R. Wilensky, "Experiments in Improving Unsupervised Word Sense Disambiguation," University of California, Berkeley, Department of EECS, Computer Science Division, Tech. Rep. 03–1227, Feb. 2003. R. Wilensky, Planning and Understanding: A Computational Approach to Human Reasoning, Advanced Book Program, Reading, MA: Addison-Wesley Publishing Co., 1983. R. Wilensky, "Understanding Goal-Based Stories," Yale University, Sep. 1978. B. Kahn and R. Wilensky, "A Framework for Distributed Digital Object Services", May 1995.
Read more →