Embedding lookup layer - An embedding lookup layer retrieves numerical vectors from an embedding table using discrete input identifiers.
Embedding matrix - An embedding matrix is a table of numerical vectors, typically with one row for each token or category and one column for each embedding dimension.
Embedding space - An embedding space is the vector space in which a model represents items as numerical coordinates.
Embedding vector - An embedding vector is an ordered list of numerical coordinates representing an item for a machine-learning task.
Embodied agent - An embodied agent perceives and acts through a body situated in an environment.
Emergent algorithm - An emergent algorithm produces a larger pattern of behavior through interactions among simpler components following local rules.
Emergent Bias - Emergent bias is systematic unfairness that becomes apparent through the interaction of a computer system with its real context of use, particularly as...
Emission probabilities - Emission probabilities describe how likely particular observations are given a hidden state in a probabilistic model such as a hidden Markov model, or HMM.
Emphatic temporal-difference learning - Emphatic temporal-difference learning is a family of value-prediction methods that changes the emphasis placed on updates to address instability in...
Empirical Bayes - Empirical Bayes is an approach that estimates aspects of a Bayesian analysis, commonly the prior distribution or its hyperparameters, from observed data.
Empirical cumulative distribution function - The empirical cumulative distribution function, or ECDF, gives the proportion of observed sample values that are less than or equal to a specified threshold.
Empirical distribution - An empirical distribution is the probability distribution that assigns equal mass to each observation in a nonempty, unweighted dataset.
Empirical dynamic modeling - Empirical dynamic modeling, or EDM, is a family of methods for studying and predicting changing systems by reconstructing their dynamics from observed...
Empirical gradient - In the local-search terminology used by Artificial Intelligence: A Modern Approach, an empirical gradient is an estimate of how an objective changes...
Empirical loss - Empirical loss is the loss measured on a finite set of observed examples, usually calculated as the average of a per-example loss function.
Empirical risk - Empirical risk is a model's average loss on a specified collection of observed examples.
Empirical risk minimization - Empirical risk minimization, or ERM, is the learning principle of choosing a model from an allowed set to minimize average loss on the training examples.
Empowerment (artificial intelligence) - In AI, empowerment is an information-theoretic measure of how much an agent's actions can influence its future observations.
Emulation - Emulation is the reproduction of relevant behavior of one system by another system so that software, users, or connected components can interact with the...
Enactive interfaces - Enactive interfaces are human - computer interfaces designed around the continuing relationship between bodily action and perception.
Encoder - An encoder is the part of a model that reads an input and compresses it into an internal numeric form that captures what matters about it for the task.
Encoder-decoder - An encoder-decoder is a model architecture in which an encoder represents an input and a decoder uses that representation to produce an output.
Encoder models - Encoder models transform an input into learned internal representations that can support prediction, matching, or extraction.
Encoding (for Features) - Encoding, for features, is converting a field into a numeric form a model can use, such as turning the category red, amber or green into numbers without...
End-to-end learning - End-to-end learning trains a system's learnable processing stages together using an objective tied to its final output.
End-to-end training - End-to-end training uses a downstream task objective to adjust parameters across a connected model, including earlier representation-building components.
Endpointing - Endpointing is deciding when a spoken utterance or input segment is complete enough for a speech system to finalize recognition or move to its next action.
Energy-based model - An energy-based model assigns a numerical energy score to a possible configuration or an input-output combination.
Energy distance - Energy distance is a measure of difference between probability distributions built from expected distances between independent observations.
Energy in frame - Energy in a frame is a measure of signal strength over a short segment of audio.
English auction - An English auction is an ascending-price auction in which participants compete through increasing bids, or remain active as a displayed price rises.
Ensemble - An ensemble is a model made by combining several models, so that their collective answer is better than any of them alone.
Ensemble Kalman filter - The ensemble Kalman filter, or EnKF, is a method for updating estimates of a changing system by combining an ensemble of model forecasts with incoming...
Ensemble learning - Ensemble learning is the discipline of training multiple models and combining them deliberately, covering the strategies, bagging, boosting and stacking...
Entailment - Entailment is a relationship in logic: a set of statements entails another statement when every interpretation that makes the starting statements true also...
Enterprise bus matrix - An enterprise bus matrix is a data-warehouse planning grid that maps business processes to the dimensions used to describe them.
Enterprise cognitive system - An enterprise cognitive system is a broad label for business software that combines AI capabilities with organisational data and workflows to support tasks...
Enterprise data modeling - Enterprise data modeling is the practice of describing the important data concepts, relationships and rules across an organization.
Enterprise data planning - Enterprise data planning is the coordinated process of deciding what an organization needs from its data and how to develop the capabilities to meet those...
Enterprise information integration - Enterprise information integration, or EII, provides a unified way to access information held in different organisational sources.
Entity-based coherence - Entity-based coherence is the continuity a text achieves through its references to people, things, organizations, and other discourse entities.
Entity grid - An entity grid is a table that represents how people, objects, and other discourse entities appear across the sentences of a document.
Entity integrity - Entity integrity is the database principle that each row must have a dependable identity, commonly enforced through a primary key whose values are unique...
Entity linking - Entity linking is the task of connecting a mention in text to the appropriate entity record in a knowledge base.
Entity-Relationship Model - The entity-relationship model is a conceptual approach to describing data through entities, their attributes, and relationships among them.
Entropic vector - An entropic vector records the joint entropies of all nonempty subsets of a collection of discrete random variables with finite entropies.
Entropically regularized optimal transport - Entropically regularized optimal transport finds a mass-transfer plan that balances low transport cost with a preference for a more spread-out plan.
Entropy - Entropy, in information theory, measures the average uncertainty associated with a probability distribution.