AI Bot Grammar Checker

AI Bot Grammar Checker — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

Voice activity detection

Voice activity detection (VAD), also known as speech activity detection or speech detection, is the detection of the presence or absence of human speech, used in speech processing. The main uses of VAD are in speaker diarization, speech coding and speech recognition. It can facilitate speech processing, and can also be used to deactivate some processes during non-speech section of an audio session: it can avoid unnecessary coding/transmission of silence packets in Voice over Internet Protocol (VoIP) applications, saving on computation and on network bandwidth. VAD is an important enabling technology for a variety of speech-based applications. Therefore, various VAD algorithms have been developed that provide varying features and compromises between latency, sensitivity, accuracy and computational cost. Some VAD algorithms also provide further analysis, for example whether the speech is voiced, unvoiced or sustained. Voice activity detection is usually independent of language. It was first investigated for use on time-assignment speech interpolation (TASI) systems. == Algorithm overview == The typical design of a VAD algorithm is as follows: There may first be a noise reduction stage, e.g. via spectral subtraction. Then some features or quantities are calculated from a section of the input signal. A classification rule is applied to classify the section as speech or non-speech – often this classification rule finds when a value exceeds a certain threshold. There may be some feedback in this sequence, in which the VAD decision is used to improve the noise estimate in the noise reduction stage, or to adaptively vary the threshold(s). These feedback operations improve the VAD performance in non-stationary noise (i.e. when the noise varies a lot). A representative set of recently published VAD methods formulates the decision rule on a frame by frame basis using instantaneous measures of the divergence distance between speech and noise. The different measures which are used in VAD methods include spectral slope, correlation coefficients, log likelihood ratio, cepstral, weighted cepstral, and modified distance measures. Independently from the choice of VAD algorithm, a compromise must be made between having voice detected as noise, or noise detected as voice (between false positive and false negative). A VAD operating in a mobile phone must be able to detect speech in the presence of a range of very diverse types of acoustic background noise. In these difficult detection conditions it is often preferable that a VAD should fail-safe, indicating speech detected when the decision is in doubt, to lower the chance of losing speech segments. The biggest difficulty in the detection of speech in this environment is the very low signal-to-noise ratios (SNRs) that are encountered. It may be impossible to distinguish between speech and noise using simple level detection techniques when parts of the speech utterance are buried below the noise. == Applications == VAD is an integral part of different speech communication systems such as audio conferencing, echo cancellation, speech recognition, speech encoding, speaker recognition and hands-free telephony. In the field of multimedia applications, VAD allows simultaneous voice and data applications. Similarly, in Universal Mobile Telecommunications Systems (UMTS), it controls and reduces the average bit rate and enhances overall coding quality of speech. In cellular radio systems (for instance GSM and CDMA systems) based on Discontinuous Transmission (DTX) mode, VAD is essential for enhancing system capacity by reducing co-channel interference and power consumption in portable digital devices. In speech processing applications, voice activity detection plays an important role since non-speech frames are often discarded. For a wide range of applications such as digital mobile radio, Digital Simultaneous Voice and Data (DSVD) or speech storage, it is desirable to provide a discontinuous transmission of speech-coding parameters. Advantages can include lower average power consumption in mobile handsets, higher average bit rate for simultaneous services like data transmission, or a higher capacity on storage chips. However, the improvement depends mainly on the percentage of pauses during speech and the reliability of the VAD used to detect these intervals. On the one hand, it is advantageous to have a low percentage of speech activity. On the other hand, clipping, that is the loss of milliseconds of active speech, should be minimized to preserve quality. This is the crucial problem for a VAD algorithm under heavy noise conditions. === Use in telemarketing === One controversial application of VAD is in conjunction with predictive dialers used by telemarketing firms. In order to maximize agent productivity, telemarketing firms set up predictive dialers to call more numbers than they have agents available, knowing most calls will end up in either "Ring – No Answer" or answering machines. When a person answers, they typically speak briefly ("Hello", "Good evening", etc.) and then there is a brief period of silence. Answering machine messages are usually 3–15 seconds of continuous speech. By setting VAD parameters correctly, dialers can determine whether a person or a machine answered the call and, if it's a person, transfer the call to an available agent. If it detects an answering machine message, the dialer hangs up. Often, even when the system correctly detects a person answering the call, no agent may be available, resulting in a "silent call". Call screening with a multi-second message like "please say who you are, and I may pick up the phone" will frustrate such automated calls. == Performance evaluation == To evaluate a VAD, its output using test recordings is compared with those of an "ideal" VAD – created by hand-annotating the presence or absence of voice in the recordings. The performance of a VAD is commonly evaluated on the basis of the following four parameters: FEC (Front End Clipping): clipping introduced in passing from noise to speech activity; MSC (Mid Speech Clipping): clipping due to speech misclassified as noise; OVER: noise interpreted as speech due to the VAD flag remaining active in passing from speech activity to noise; NDS (Noise Detected as Speech): noise interpreted as speech within a silence period. Although the method described above provides useful objective information concerning the performance of a VAD, it is only an approximate measure of the subjective effect. For example, the effects of speech signal clipping can at times be hidden by the presence of background noise, depending on the model chosen for the comfort noise synthesis, so some of the clipping measured with objective tests is in reality not audible. It is therefore important to carry out subjective tests on VADs, the main aim of which is to ensure that the clipping perceived is acceptable. In VoIP applications, front-end clipping can be reduced by rewinding to shortly before the detection and sending very slightly delayed data. This kind of test requires a certain number of listeners to judge recordings containing the processing results of the VADs being tested, giving marks to several speech sequences on the following features: Quality; Comprehension difficulty; Audibility of clipping. These marks are then used to calculate average results for each of the features listed above, thus providing a global estimate of the behavior of the VAD being tested. To conclude, whereas objective methods are very useful in an initial stage to evaluate the quality of a VAD, subjective methods are more significant. As they require the participation of several people for a few days, increasing cost, they are generally only used when a proposal is about to be standardized. == Implementations == One early standard VAD is that developed by British Telecom for use in the Pan-European digital cellular mobile telephone service in 1991. It uses inverse filtering trained on non-speech segments to filter out background noise, so that it can then more reliably use a simple power-threshold to decide if a voice is present. The G.729 standard calculates the following features for its VAD: line spectral frequencies, full-band energy, low-band energy (<1 kHz), and zero-crossing rate. It applies a simple classification using a fixed decision boundary in the space defined by these features, and then applies smoothing and adaptive correction to improve the estimate. The GSM standard includes two VAD options developed by ETSI. Option 1 computes the SNR in nine bands and applies a threshold to these values. Option 2 calculates different parameters: channel power, voice metrics, and noise power. It then thresholds the voice metrics using a threshold that varies according to the estimated SNR. The Speex audio compression library uses a procedure named Improved Minima Controlled Recursive Averaging, which uses a smoothed representation of spectral pow
Read more →
The Best Free AI Video Editor for Beginners

Comparing the best AI video editor? An AI video editor 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 video editor 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 →
Simon Godsill

Simon John Godsill (born 2 December 1965) is professor of statistical signal processing at the University of Cambridge, and a professorial fellow at Corpus Christi College. He is also a member of the Centre for Science and Policy. His main area of research is Bayesian statistics and stochastic sampling methodologies, particularly particle filtering. == Education == Godsill obtained both undergraduate and Ph.D. degrees from the Department of Engineering at Cambridge University, whilst a member of Selwyn College. He obtained a first class degree in the Electrical and Information Sciences Tripos. The title of his 1993 Ph.D. thesis was "The Restoration of Degraded Audio Signals" and his Ph.D. supervisor was Peter Rayner, whom he shared with Michael Richard Lynch. == Career == Godsill has published over 250 articles in peer reviewed journals, along with the books Digital audio restoration: a statistical model based approach and Compressed sensing & sparse filtering. == Business interests == Godsill is currently a director of CEDAR Audio Ltd, a Cambridge-based company that applies Bayesian mathematics for purposes of noise reduction in audio data. In February 2005, the company received a Sci-Tech Academy Award (a 'Technical Oscar') for its services to the movie industry, and a stream of innovations appeared over the following years with corresponding recognition including induction into the Audio Technology Hall of Fame (2008), a Cinema Audio Society Award (2009). Godsill is also a director at Input Dynamics Ltd, a Cambridge-based company that applies Bayesian techniques to touch screen technology. Godsill is involved with the research effort at BMLL Technologies, a Cambridge spin-off working in the field of machine learning application in the financial sector.
Read more →
Deepti Gurdasani

Deepti Gurdasani is a British-Indian clinical epidemiologist and statistical geneticist who is a senior lecturer in machine learning at the Queen Mary University of London. Her research considers the genetic diversity of African Populations. Throughout the COVID-19 pandemic, Gurdasani has provided the public with her analysis of the evolving situation mainly on the Twitter platform. == Early life and education == Gurdasani was an undergraduate and medical student at the Christian Medical College Vellore at Tamil Nadu Dr. M.G.R. Medical University. After earning her medical degree and qualifying in internal medicine, she moved to the United Kingdom, where she worked toward a research doctorate in genetic epidemiology at Wolfson College, Cambridge. Her doctoral research involved the design of strategies to understand complex diseases in diverse populations. == Research and career == In 2013, Gurdasani joined the Wellcome Sanger Institute as a postdoctoral fellow, where she worked on the genomic diversity of African populations and how this diversity impacts susceptibility to disease. She makes use of dense genotypes and whole genome sequences to better understand how population movements determined genetic structure. In particular, Gurdasani develops machine learning algorithms to large-scale clinical data sets. At the Sanger Gurdasani co-led the African Genome Variation Project and the Uganda Resource Project. Gurdasani moved to Queen Mary University of London in 2019, where she created deep learning approaches for clinical prediction and the identification of novel, genome-based drug targets. During the COVID-19 pandemic Gurdasani has provided public commentary on the pandemic, making use of both Twitter and print media to share information on the evolving situation. She has researched the incidence of long covid in the UK. In 2021 Gurdasani started to write for The Guardian. == Selected publications == Deepti Gurdasani; Tommy Carstensen; Fasil Tekola-Ayele; et al. (3 December 2014). "The African Genome Variation Project shapes medical genetics in Africa". Nature. 517 (7534): 327–332. doi:10.1038/NATURE13997. ISSN 1476-4687. PMC 4297536. PMID 25470054. Wikidata Q34979569. Nisreen A Alwan; Rochelle Ann Burgess; Simon Ashworth; et al. (15 October 2020). "Scientific consensus on the COVID-19 pandemic: we need to act now". The Lancet. doi:10.1016/S0140-6736(20)32153-X. ISSN 0140-6736. PMC 7557300. PMID 33069277. Wikidata Q100697134. Deepti Gurdasani; Inês Barroso; Eleftheria Zeggini; Manjinder S Sandhu (24 June 2019). "Genomics of disease risk in globally diverse populations". Nature Reviews Genetics. 20 (9): 520–535. doi:10.1038/S41576-019-0144-0. ISSN 1471-0056. PMID 31235872. Wikidata Q93000887. (erratum)
Read more →
Explanation-based learning

Explanation-based learning (EBL) is a form of machine learning that exploits a very strong, or even perfect, domain theory (i.e. a formal theory of an application domain akin to a domain model in ontology engineering, not to be confused with Scott's domain theory) in order to make generalizations or form concepts from training examples. It is also linked with Encoding (memory) to help with Learning. == Details == An example of EBL using a perfect domain theory is a program that learns to play chess through example. A specific chess position that contains an important feature such as "Forced loss of black queen in two moves" includes many irrelevant features, such as the specific scattering of pawns on the board. EBL can take a single training example and determine what are the relevant features in order to form a generalization. A domain theory is perfect or complete if it contains, in principle, all information needed to decide any question about the domain. For example, the domain theory for chess is simply the rules of chess. Knowing the rules, in principle, it is possible to deduce the best move in any situation. However, actually making such a deduction is impossible in practice due to combinatoric explosion. EBL uses training examples to make searching for deductive consequences of a domain theory efficient in practice. In essence, an EBL system works by finding a way to deduce each training example from the system's existing database of domain theory. Having a short proof of the training example extends the domain-theory database, enabling the EBL system to find and classify future examples that are similar to the training example very quickly. The main drawback of the method—the cost of applying the learned proof macros, as these become numerous—was analyzed by Minton. === Basic formulation === EBL software takes four inputs: a hypothesis space (the set of all possible conclusions) a domain theory (axioms about a domain of interest) training examples (specific facts that rule out some possible hypothesis) operationality criteria (criteria for determining which features in the domain are efficiently recognizable, e.g. which features are directly detectable using sensors) == Application == An especially good application domain for an EBL is natural language processing (NLP). Here a rich domain theory, i.e., a natural language grammar—although neither perfect nor complete, is tuned to a particular application or particular language usage, using a treebank (training examples). Rayner pioneered this work. The first successful industrial application was to a commercial NL interface to relational databases. The method has been successfully applied to several large-scale natural language parsing systems, where the utility problem was solved by omitting the original grammar (domain theory) and using specialized LR-parsing techniques, resulting in huge speed-ups, at a cost in coverage, but with a gain in disambiguation. EBL-like techniques have also been applied to surface generation, the converse of parsing. When applying EBL to NLP, the operationality criteria can be hand-crafted, or can be inferred from the treebank using either the entropy of its or-nodes or a target coverage/disambiguation trade-off (= recall/precision trade-off = f-score). EBL can also be used to compile grammar-based language models for speech recognition, from general unification grammars. Note how the utility problem, first exposed by Minton, was solved by discarding the original grammar/domain theory, and that the quoted articles tend to contain the phrase grammar specialization—quite the opposite of the original term explanation-based generalization. Perhaps the best name for this technique would be data-driven search space reduction. Other people who worked on EBL for NLP include Guenther Neumann, Aravind Joshi, Srinivas Bangalore, and Khalil Sima'an.
Read more →
AI Headshot Generators: Free vs Paid (2026)

Curious about the best AI headshot generator? An AI headshot 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 headshot 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 →
Samer Hassan

Samer Hassan is a computer scientist, social scientist, activist and researcher, focused on the study of the collaborative economy, online communities and decentralized technologies. He is an associate professor at Universidad Complutense de Madrid (Spain) and Faculty Associate at the Berkman Klein Center for Internet & Society at Harvard University. He is the recipient of an ERC Grant of 1.5M€ with the P2P Models project, to research blockchain-based decentralized autonomous organizations for the collaborative economy. == Education and career == Hassan is a Spanish/Lebanese scholar with an interdisciplinary background, which combines computer sciences with social sciences and activism. He received a degree in Computer Science and MSc in Artificial Intelligence from the Universidad Complutense de Madrid (UCM) in Spain. He also studied three years of Political Science at the distance learning university UNED. He then pursued a PhD in Social Simulation at the department of Software Engineering and Artificial Intelligence of UCM, supervised by the computer scientist Juan Pavón and the sociologist Millán Arroyo-Menéndez. He has been researching in several institutions, funded by several scholarships and awards, most notably Harvard's Real Colegio Complutense, and the Spanish postdoctoral grants Juan de la Cierva and José Castillejo. Thus, he was a visiting researcher at the Centre for Research in Social Simulation, in the Department of Sociology at the University of Surrey in the UK, working under the supervision of Nigel Gilbert (2007-2008), and a lecturer at the American University of Science and Technology in Lebanon (2010–11). He was selected as Fellow at the Berkman Klein Center for Internet & Society at Harvard University (2015-2017) and is presently a Faculty Associate at the same structure. Starting in 2024, he joined, as affiliate faculty, the Institute for Digital Cooperative Economy (The New School), part of the Platform Cooperativism Consortium. == Activism and social engagement == As an activist, Hassan has been engaged in both offline (La Tabacalera de Lavapiés, Medialab-Prado) and online (Ourproject.org, Barrapunto, Wikipedia) initiatives. He was accredited as a grassroots facilitator by the Altekio Cooperative. He co-founded the Comunes Nonprofit in 2009 and the Move Commons webtool project in 2010. He has co-organized practitioner-oriented workshops on platform co-ops and free/open source decentralized tools for communities, and has presented his work in non-academic conferences of Mozilla, the Internet Archive, and others. As a privacy advocate, he co-created a course on cyber-ethics which has been teaching since 2013 (as of 2021). He was co-founder of the Sci-Fdi Spanish science-fiction magazine. His gender is non-binary and uses he/they pronouns. == Work == Hassan's interdisciplinary research spans multiple fields, including online communities, online governance, online collaboration, decentralized technologies, blockchain-based decentralized autonomous organizations, free/libre/open source software, Commons-based peer production, agent-based social simulation, social movements and cyberethics. He has published more than 60 works in these fields. Hassan's PhD thesis focused on the methodological challenges for building data-driven social simulation models. The main model built simulated the transition from modern values to postmodern values in Spain. His methodological work also explored the combination of different artificial intelligence technologies, i.e. software agents with fuzzy logic, data mining, natural language processing, and microsimulation. In his postdoctoral period, he focused on experimenting with multiple software systems to facilitate the collaborative economy, e.g. semantic-web labelling for commons-based initiatives, distribution of value in peer production communities, agent-supported online assemblies, decentralized real-time collaborative software, decentralized blockchain based reputation, or blockchain-enabled commons governance. Hassan was Principal Investigator of the UCM partner in the EU-funded P2Pvalue project on building decentralized web-tools for collaborative communities. As such, he led the team that created SwellRT, a federated backend-as-a-service focused to ease development of apps featuring real-time collaboration. Intellectual Property of this project was transferred to the Apache Software Foundation in 2017. As part of this research line, Hassan's team also develop two SwellRT-based apps, "Teem" for management of social collectives and Jetpad, a federated real time editor. He presented the innovations concerning these software at Harvard's Berkman Klein Center and Harvard's Center for Research on Computation and Society. Other research lines offered outcomes beyond publications. "Wikichron", coled by Javier Arroyo, is a web tool to visualize MediaWiki community metrics, currently in production and available for third-parties. "Decentralized Science", led by Hassan's PhD student Ámbar Tenorio-Fornés, is a framework to facilitate decentralized infrastructure and open peer review in the scientific publication process, which has been selected by the European Commission to receive funding as a spin-off social enterprise. His research on blockchain and crowdfunding models awarded him with a commission from Triple Canopy. His team pushed forward a mapping of the ecosystem of blockchain for social good, led by the Joint Research Centre and published by the European Commission. As part of his ERC project P2P Models, Hassan and his team –including Silvia Semenzin– are investigating whether blockchain technology and Decentralized Autonomous Organizations could contribute to improving the governance of commons-oriented communities, both online and offline. Their work has been showcased for tackling the impact of blockchain on governance, proposing alternatives to the current sharing economy, emerging forms of techno-social systems like NFTs or prediction markets, or giving relevance to gender issues in the field. Hassan was invited to present the project achievements in Harvard Kennedy School, MIT Media Lab, Harvard's Data Privacy Lab, Harvard's Center for Research on Computation and Society, and Harvard's SEAS EconCS. British MP and Opposition Leader Ed Miliband showcased his research and its potential impact on policy. The project made public its way of organizing and its core values. In particular, it has shown a commitment to diversity as a core value in hiring, or choosing case studies. == Selected works == Arroyo, Javier; Davó, David; Martínez-Vicente, Elena; Faqir-Rhazoui, Youssef; Hassan, Samer (8 November 2022). "DAO-Analyzer: Exploring Activity and Participation in Blockchain Organizations" (PDF). Companion Publication of the 2022 Conference on Computer Supported Cooperative Work and Social Computing. CSCW'22 Companion. New York, NY, USA: Association for Computing Machinery. pp. 193–196. doi:10.1145/3500868.3559707. ISBN 978-1-4503-9190-0. Rozas, David; Tenorio-Fornés, Antonio; Díaz-Molina, Silvia; Hassan, Samer (2021). "When Ostrom Meets Blockchain: Exploring the Potentials of Blockchain for Commons Governance". SAGE Open. 11 (1): 215824402110025. doi:10.1177/21582440211002526. ISSN 2158-2440. Faqir-Rhazoui, Youssef; Ariza-Garzón, Miller-Janny; Arroyo, Javier; Hassan, Samer (8 May 2021). "Effect of the Gas Price Surges on User Activity in the DAOs of the Ethereum Blockchain" (PDF). Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems. CHI EA '21. New York, NY, USA: Association for Computing Machinery. pp. 1–7. doi:10.1145/3411763.3451755. ISBN 978-1-4503-8095-9. Hassan, Samer; Filippi, Primavera De (20 April 2021). "Decentralized Autonomous Organization". Internet Policy Review. 10 (2). doi:10.14763/2021.2.1556. hdl:10419/235960. ISSN 2197-6775. Joint Research Centre (European Commission); Hassan, Samer; Hakami, Anna; Brekke, Jaya Klara; De Filippi, Primavera; Lopéz Morales, Genoveva; Pólvora, Alexandre; Orgaz Alonso, Christian; Bodó, Balázs (2020). Scanning the European ecosystem of distributed ledger technologies for social and public good: what, why, where, how, and ways to move forward. LU: Publications Office of the European Union. doi:10.2760/300796. ISBN 978-92-76-21578-3. Filippi, Primavera De; Hassan, Samer (14 November 2016). "Blockchain technology as a regulatory technology: From code is law to law is code". First Monday. arXiv:1801.02507. doi:10.5210/fm.v21i12.7113. ISSN 1396-0466.
Read more →
Bibliotheca Polyglotta

The Bibliotheca Polyglotta is a Norwegian database for Multilingualism project, lingua franca and science per global history at the University of Oslo. The aim of the project is according to pages is "producing a web corpus of Buddhist texts for using in multilingual lexicography. More generally, will the texts used for the study Sanskrit, Chinese and Tibetan."
Read more →
Jordan Antiquities Database and Information System

The Jordan Antiquities Database and Information System (JADIS) was a computer database of antiquities in Jordan, the first of its kind in the Arab world. It was established by the Department of Antiquities in 1990, in cooperation with the American Center for Oriental Research in Amman and sponsored by the United States Agency for International Development. JADIS was in use until 2002, when it was superseded by a new system, MEGA-J. Over 10,841 antiquities were registered in the database. An introduction and printed summary of the database was published by the Department of Antiquities in 1994, edited by Gaetano Palumbo.
Read more →
AI Virtual Assistants: Free vs Paid (2026)

Trying to pick the best AI virtual assistant? An AI virtual assistant is software that uses machine learning to help you get more done — it scales effortlessly from a single task to thousands. The best picks balance beginner-friendly simplicity with the depth power users need, and they ship updates often. Whether you are a beginner or a pro, the right AI virtual assistant 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 →
Best AI Background Removers in 2026

Comparing the best AI background remover? An AI background remover 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 background remover 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 →
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 →
AppyStore

AppyStore is a comprehensive learning videos and games app for kids up to the age of 8 years. The platform developed by Mauj Mobile, a mobile value-added services (VAS) provider curates content to help in child development by leveraging technology. Mauj is funded by Sequoia Capital, Westbridge Capital and Intel Capital. == Background == AppyStore was launched in 2014 as a platform providing content for kids between the ages of 1.5 and 6 years. AppyStore subsequently extended its services for kids up to 8 years of age. The company operates on a subscription-based model and claims to have 5,000 learning games and videos segregated in 18 learning areas developed to help children gain optimal skills and qualities. According to an article published in Business Standard, the application is claimed to be one of the top 5 apps that help to enhance the logical and imaginative capabilities of children. AppyStore was awarded the Best app for kids by Google Play in December 2017. == Service == The company provides content via a website and an Android app. The website and android app provide learning games, rhymes, phonics, reading, stories, science, numbers, maths, logic videos comprising puzzles, worksheets, videos and fun activities and the premium subscription also includes physical worksheets which are home delivered. This content is educational and has been handpicked by teachers and experts with an understanding of the major areas of child development milestones for children up to 8 years of age. The mobile application also allows parents to track the progress of their child on the basis of the number of videos viewed.
Read more →
Multiline optical-character reader

A multiline optical-character reader, or MLOCR, is a type of mail sorting machine that uses optical character recognition (OCR) technology to determine how to route mail through the postal system. MLOCRs work by capturing images of the front of letter-sized mailpieces, and extracting the entire address from each piece. It looks up the postal code within each address in a master database, prints a barcode representing this information on the mailpiece, and performs an initial sort. All of this occurs in a fraction of a second as the mailpiece passes through the machine. After this point, mail is further sorted by barcode sorters that read this barcode to determine its destination throughout its journey all the way down to the walk sequence of the mail carrier. The United States Postal Service has used remote bar coding since 1992. In the United States, if the MLOCR is not able to decode the address, then the mailpiece is placed on "hold" by printing a unique fluorescent barcode on the back of the mailpiece, and the mailpiece is then set aside for further processing by the Remote Bar Coding System (formerly called Remote Video Encoding). An image of the mailpiece is sent to a Remote Encoding Center where a human data conversion operator manually inspects the image. The operator converts the information on the mailpiece into abbreviated codes and enters the data into the computer. This data is sent back to the MLOCR site where it is matched with the unique barcode on the back of the un-coded mailpiece, and a barcode is then printed on the mailpiece like the rest of the mail. All this effort is invested up front into deciphering the destination of each mailpiece and printing the correct barcode, so that the mailpiece will never need to be manually examined again until it reaches the hands of the letter carrier who will carry it to the final delivery point. A Delivery Bar Code Sorter is repeatedly used at each point in the USPS system to read the barcode and sort the mailpiece to a tray corresponding to the next leg of its journey towards its final destination. The United States Postal Service is the largest user of these machines; however, large volume mailers and mail consolidators also have their own MLOCR systems to barcode outgoing mail in order to receive significant postage discounts. An option called FASTforward can be added to an MLOCR that allows it to automatically forward mail to a new address. This additional computer hardware/software combination looks up decoded addresses in the National Change of Address database to see if the recipient has recently moved. If so, a POSTNET barcode representing the new address is sprayed on the mailpiece thus routing it to new address although the old address is still visible—a testament to the degree at which mail can be mechanically sorted. Generally, all OCR-equipped letter sorting machines ordered since the late 1980s have been equipped with OCR systems capable of reading multiple lines of address.
Read more →
Rada Mihalcea

Rada Mihalcea is the Janice M. Jenkins Collegiate Professor of Computer Science and Engineering at the University of Michigan. She has made significant contributions to natural language processing, multimodal processing, computational social science, and AI for Social Good. With Paul Tarau, she invented the TextRank Algorithm, which is a classic algorithm widely used for text summarization. == Career == Mihalcea has a Ph.D. in Computer Science and Engineering from Southern Methodist University (2001) and a Ph.D. in Linguistics, Oxford University (2010). In 2017 she was named Director of the Artificial Intelligence Laboratory at University of Michigan, Computer Science and Engineering. In 2018, Mihalcea was elected as vice president for the Association for Computational Linguistics (ACL). In 2021, she was elected the president for ACL. She is a professor of Computer Science and Engineering at the University of Michigan, where she also leads the Language and Information Technologies (LIT) Lab. Before joining UofM, she was a professor at North Texas University between 2002-2013. A prolific researcher, Mihalcea has authored or coauthored over 500 articles since 1998 on topics ranging from semantic analysis of text to lie detection. Her work has been cited over 50,000 times on Google Scholar, which made her one of the most cited scholars in Multimodal Interaction and Computational Social Science. In 2008, Mihalcea received the Presidential Early Career Award for Scientists and Engineers (PECASE) She is an ACM Fellow (since 2019), AAAI Fellow (since 2021), and ACL Fellow (since 2025). Mihalcea is an outspoken promoter of diversity in computer science. She also supports an expansion of the traditional analysis of educational success, which tends to focus on academic behaviour, to include student life, personality and background outside of the classroom. Mihalcea leads Girls Encoded, a program designed to develop the pipeline of women in computer science as well as to retain the women who have entered into the program. == Awards == Elected to American Academy of Arts & Sciences, 2026 ACL Fellow, 2025 "for significant contributions to graph-based language processing, computational social science, and the advancement of NLP for social good." AAAI Fellow, 2021 "for significant contributions to natural language processing and computational social science". ACM Fellow, 2019 "for contributions to natural language processing, with innovations in data-driven and graph-based language processing". Sarah Goddard Power Award, 2019. Carol Hollenshead Award, 2018. Presidential Early Career Award for Scientists and Engineers (PECASE), 2009. Awarded by President Barack Obama. == Research == Mihalcea is known for her research in natural language processing, multimodal processing, computational social sciences. In a collaboration she leads at the University of Michigan, Mihalcea has created software that can detect human lying. In a study of video clips of high profile court cases, a computer was more accurate at detecting deception than human judges. Mihalcea's lie-detection software uses machine learning techniques to analyze video clips of actual trials. In her 2015 study, the team used clips from The Innocence Project, a national organization that works to reexamine cases where individuals were tried without the benefit of DNA testing with the aim of exonerating wrongfully convicted individuals. After identifying common human gestures, they transcribed the audio from the video clips of trials and analyzed how often subjects labeled deceptive used various words and phrases. The system was 75% accurate in identifying which subjects were deceptive among 120 videos. That puts Mihalcea's algorithm on par with the most commonly accepted form of lie detection, polygraph tests, which are roughly 85 percent accurate when testing guilty people and 56 percent accurate when testing the innocent. She notes there are still improvements to be made — in particular to account for cultural and demographic differences. A possibly unique advantage of Mihalcea's study was the real world, high stakes nature of the footage analyzed in the study. In laboratory experiments, it is difficult to create a setting that motivates people to truly lie. In 2018, Mihalcea and her collaborators worked on an algorithm-based system that identifies linguistic cues in fake news stories. It successfully found fakes up to 76% of the time, compared to a human success rate of 70%. == Publications == === Books === Rada Mihalcea and Dragomir Radev, Graph-based Natural Language Processing and Information Retrieval, Cambridge U. Press, 2011. Gabe Ignatow and Rada Mihalcea, Text Mining: A Guidebook for the Social Sciences, SAGE, 2016. Gabe Ignatow and Rada Mihalcea, An Introduction to Text Mining: Research Design, Data Collection, and Analysis, SAGE, 2017. === Journals and conferences === Textrank: Bringing order into text. R. Mihalcea, P. Tarau. Proceedings of the 2004 conference on empirical methods in natural language processing. 2004 Corpus-based and knowledge-based measures of text semantic similarity. R. Mihalcea, C. Corley, C. Strapparava. AAAI 6, 775-780. 2006 Wikify!: linking documents to encyclopedic knowledge. R. Mihalcea, A. Csomai. Proceedings of the sixteenth ACM conference on Conference on information and information management. 2007 Learning to identify emotions in text. C. Strapparava, R. Mihalcea. Proceedings of the 2008 ACM symposium on Applied computing, 1556-1560. 2008 Semeval-2007 task 14: Affective text. C. Strapparava, R. Mihalcea. Proceedings of the Fourth International Workshop on Semantic Evaluations. 2007 Learning multilingual subjective language via cross-lingual projections. R. Mihalcea, C. Banea, J. Wiebe. Proceedings of the 45th annual meeting of the association of computational linguistics. 2007 Graph-based ranking algorithms for sentence extraction, applied to text summarization. R. Mihalcea. Proceedings of the ACL Interactive Poster and Demonstration Sessions. 2004 Falcon: Boosting knowledge for answer engines. S. Harabagiu, D. Moldovan, M. Pasca, R. Mihalcea, M. Surdeanu, Razvan Bunescu, Roxana Girju, Vasile Rus, Paul Morarescu. TREC 9, 479-488. 2000 Measuring the semantic similarity of texts. C. Corley, R. Mihalcea. Proceedings of the ACL workshop on empirical modeling of semantic equivalence and entailment. 2005 R Mihalcea (2007). "Using wikipedia for automatic word-sense disambiguation". Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference. CiteSeerX 10.1.1.74.3561. - see also Word-sense disambiguation Unsupervised graph-based word sense disambiguation using measures of word semantic similarity. R. Sinha, R. Mihalcea. International Conference on Semantic Computing (ICSC 2007), 363-369. 2007 == Personal life == Mihalcea was born in Cluj-Napoca, Romania, where she attended the Technical University of Cluj-Napoca. She can speak Romanian, English, Italian, and French. Mihalcea has two children - Zara (b. 2009) and Caius (b. 2013). They were both born in Dallas, Texas. She is married to an associate professor of engineering at the University of Michigan–Flint - Mihai Burzo. They met while they were both completing Ph.D.s at Southern Methodist University in 2001 and have often collaborated on research, such as the 2015 study on lie detection.
Read more →