3,135 articles
Wavelet neural network
A wavelet neural network, or wavelet network, is a one-hidden-layer neural network whose hidden units use wavelet activation functions, proposed by Zhang and Benveniste in 1992.
WaveNet
WaveNet, also known as DeepMind WaveNet, is a neural network model of raw audio introduced by Google DeepMind in September 2016, led by Aaron van den Oord.
Wayve
Wayve Technologies is a British artificial intelligence company headquartered in London, founded in 2017 by Alex Kendall and Amar Shah, developing end-to-end deep learning systems for automated driving.
Weak supervision
Weak supervision is a machine learning approach that trains models from cheap, noisy, or coarse labels instead of hand-labeled data, covering incomplete, inexact, and inaccurate supervision.
Weakly supervised learning
Weakly supervised learning trains machine learning models from incomplete, inexact, or inaccurate labels instead of costly fully annotated ground truth, covering detection, segmentation, and classification.
Weakly supervised object detection
Weakly supervised object detection (WSOD) trains models to classify and locate objects in images using only cheap image-level class labels instead of costly bounding-box annotations.
Web of Science
Web of Science, also known as Web of Knowledge, is a subscription citation database owned by Clarivate that indexes scholarly journals, books, and conference proceedings.
Web Ontology Language
The Web Ontology Language (OWL) is a W3C-standardized Semantic Web language for representing rich knowledge in a form computer programs can reason over, first published in 2004.
Weight decay
Weight decay is a regularization technique for training neural networks in which weights are multiplicatively shrunk toward zero each step, traditionally by adding an L2 penalty to the loss function.
Weight initialization
Weight initialization, also called parameter initialization, is the assignment of starting values to a neural network's weights before training, since poor scaling can keep deep networks from training at all.
Weighted ensemble simulation
Weighted ensemble (WE) simulation is a path-sampling method that runs many short, unbiased trajectory segments in parallel, adjusting their statistical weights to estimate rare events and long-timescale kinetics.
Weisfeiler-Lehman Network
The Weisfeiler-Lehman Network (WLN) is a graph neural network proposed by MIT researchers at NIPS 2017 that predicts organic reaction products by identifying the reaction center, outperforming template-based methods.
Westlaw
Westlaw is an online legal research service owned by Thomson Reuters that provides searchable case law, statutes, and regulations with the KeyCite citator and AI research tools.
Whale optimization algorithm
The whale optimization algorithm (WOA) is a swarm intelligence metaheuristic proposed by Seyedali Mirjalili and Andrew Lewis in 2016, modeled on humpback whale bubble-net hunting.
Wheatley (Portal)
Wheatley is a fictional robot character in Valve's 2011 puzzle game Portal 2, formally the Intelligence Dampening Sphere, a bumbling personality core voiced by the English comedian Stephen Merchant.
WhyLabs
WhyLabs (WhyLabs, Inc.) was a Seattle AI observability company founded in 2019, maker of the AI Control Center and open-source whylogs and LangKit; it raised $14M, was reportedly acquired by Apple in 2025, then discontinued operations and open-sourced its platform.
whylogs
whylogs is WhyLabs' open source, Apache-2.0 data logging library that generates compact, mergeable statistical profiles of datasets for drift, data quality, and ML monitoring; its commercial host WhyLabs shut down in 2025.
Wide neural network
A wide neural network is one with very large hidden layers, often studied in an infinite-width limit where training simplifies to kernel methods such as the neural tangent kernel.
Wikidata
Wikidata, also known as Wikidata.org, is a free multilingual knowledge base of structured data that the Wikimedia Foundation launched in 2012 to supply other Wikimedia projects.
Wikipedia
Wikipedia is a free, web-based encyclopedia written and edited by volunteers and hosted by the Wikimedia Foundation, launched on January 15, 2001 as the offshoot of the expert-written Nupedia.
WikiSQL
WikiSQL is a 2017 Salesforce text-to-SQL benchmark of 80,654 crowd-annotated question-SQL pairs over 24,241 Wikipedia tables, introduced with Seq2SQL, restricted to simple single-table queries, later criticized as saturated and superseded by Spider and BIRD.
WikiText-103
WikiText-103 is a word-level language modeling dataset of over 103 million tokens from verified Good and Featured English Wikipedia articles, introduced in 2016 by Salesforce Research.
Wildcard character
A wildcard character is a symbol in a search pattern that stands for one or more characters, used in shell globbing, SQL LIKE queries, and regular expressions.
Window function
A window function, also called a tapering or apodization function, weights a finite signal segment before Fourier analysis, reducing spectral leakage at the cost of frequency resolution.
Word alignment
Word alignment is the natural language processing task of identifying which words in a source sentence correspond to words in its translation, central to statistical machine translation.
Word count
Word count is the number of words in a document or passage, used to enforce submission limits, track writing progress, price translation work, and estimate reading time.
Word embedding
A word embedding (also word vector) is a learned vector representation of a word in which words used in similar contexts end up close together.
Word error rate
Word error rate (WER) is the standard metric for evaluating automatic speech recognition systems, counting substitutions, deletions, and insertions against a reference transcript, with lower scores being better.
Word segmentation
Word segmentation is the task of dividing running text into words for languages like Chinese, Japanese, and Thai, whose writing systems do not mark word boundaries with spaces.
Word-sense disambiguation
Word-sense disambiguation (WSD) is the natural language processing task of deciding which meaning of an ambiguous word is intended in context, using a sense inventory.