W-shingling - W-shingling represents a document using overlapping sequences of w consecutive tokens, called shingles.
W-test - The W-test is an association test developed for categorical genetic data and a binary outcome, including analysis of joint genotype categories for pairs of...
Wait list control group - A wait list control group is a comparison group scheduled to receive an intervention after an initial waiting period, while another group receives it earlier.
Wake-sleep algorithm - The wake-sleep algorithm trains a probabilistic generative model together with a recognition model by alternating two phases.
Wake word - Definition: A wake word is a designated spoken word or phrase that a system detects to activate a listening or interaction mode.
Wald's maximin model - Wald's maximin model is a decision rule that selects the action with the best worst-case payoff among the states considered possible.
Wald test - A Wald test evaluates a parameter restriction by measuring how far an estimated parameter lies from its null value relative to its estimated uncertainty.
Wald - Wolfowitz runs test - The Wald-Wolfowitz runs test examines whether the ordering of a binary sequence is consistent with randomness, commonly conditional on the numbers of each...
Walks - Walks are sequences of vertices connected by successive edges in a graph. Unlike simple paths, walks may repeat vertices and edges.
Ward histogram-based tone mapping - Ward histogram-based tone mapping is a high-dynamic-range image reproduction approach that adjusts a luminance histogram to fit a display's range while...
Warp (image warping) - An image warp is a geometric transformation that changes where image content appears by mapping coordinates between a source image and a destination image.
Warped linear predictive coding - Warped linear predictive coding is an audio-coding approach that models a signal using linear prediction on a nonuniform frequency scale.
Wasserstein GAN - A Wasserstein GAN, or WGAN, is a generative adversarial network trained using an objective based on the Wasserstein-1 distance between distributions.
Wasserstein loss - Wasserstein loss is an objective based on a Wasserstein distance between probability distributions.
Watershed segmentation - Watershed segmentation is an image-partitioning method that treats a numerical image as a landscape and separates the regions reached by competing floods.
Watkins Q(lambda) - Watkins Q(lambda) is an off-policy reinforcement-learning control method that combines Q-learning with eligibility traces.
Wavefront coding - Wavefront coding is a computational imaging approach that deliberately modifies an optical system's phase response and then digitally reconstructs the...
Waypoint - A waypoint is a specified location used to organize navigation or another spatial task.
Weak connectivity - Weak connectivity is a property of a directed graph: the graph becomes connected when edge directions are ignored.
Weak learner - A weak learner is a learning algorithm that can produce a predictor with a modest advantage over a specified baseline under stated conditions.
Weak learning - Weak learning is the ability to produce a predictor with a meaningful advantage over a specified baseline, rather than requiring arbitrarily high accuracy...
Weak supervision - Weak supervision trains machine-learning models using supervision that is less complete, precise or reliable than carefully verified labels for every example.
Web data integration - Web data integration is the process of bringing information from different web-accessible sources into a coherent form for use together.
Web intelligence - Web intelligence is a research and application area that combines artificial intelligence with web-related information technologies.
Web query classification - Web query classification is assigning a web-search query to one or more defined categories, such as a subject area or a type of search intent.
Web resource - A web resource is something identified within the Web's architecture, commonly by a Uniform Resource Identifier, or URI.
Web scraping - Web scraping is the automated extraction of selected information from web pages into a form that can be stored or analyzed.
Web search - Web search is the application of information retrieval to material available on the World Wide Web.
Webometrics - Webometrics is the quantitative study of information resources, relationships, and activity on the World Wide Web, drawing particularly on bibliometric and...
Weibull distribution - The Weibull distribution is a flexible continuous distribution for nonnegative quantities, widely used for time-to-event and reliability models.
Weight - A weight is a numerical factor that controls how strongly a value contributes to a calculation.
Weight decay - Weight decay is a training technique that repeatedly shrinks selected model weights toward zero.
Weight initialization - Weight initialization is the choice of starting values for a neural network's trainable weights before optimization begins.
Weight space - Weight space is the set of possible settings of a model's adjustable weights.
Weight tying - Definition: Weight tying makes two or more parts of a neural network use the same trainable parameters.
Weighted A* search - Weighted A* search is a best-first search method that prioritizes a state using f(n) = g(n) + W*h(n), where g is the path cost already incurred, h estimates...
Weighted Alternating Least Squares - Weighted Alternating Least Squares, or WALS, is an algorithm for fitting matrix-factorization models by repeatedly solving weighted least-squares problems...
Weighted average - A weighted average combines values while giving each a specified relative influence.
Weighted correlation network analysis - Weighted correlation network analysis is a method for exploring patterns of association among many measured variables by representing them as a network with...
Weighted graph - A weighted graph is a graph whose edges have numerical values called weights.
Weighted least squares - Weighted least squares fits a model by minimizing a sum of squared prediction errors in which each observation has a nonnegative weight.
Weighted linear function - A weighted linear function combines numerical features by multiplying each feature by a coefficient and adding the results.
Weighted majority algorithm (machine learning) - The weighted majority algorithm combines predictions from several experts by assigning each a weight, predicting with the weighted vote and reducing the...
Weighted model counting - Weighted model counting is the task of summing the weights of all truth assignments that satisfy a logical formula.
Weighted sum - A weighted sum adds values after multiplying each by an associated weight.
Weighted training set - A weighted training set assigns a numerical weight to each training example, allowing examples to contribute differently to learning.
Weighted zone scoring - Weighted zone scoring ranks a document by combining Boolean query matches from different parts, or zones, of that document.