Automation - Automation is the use of technology to perform tasks with reduced human involvement, following defined rules or trained behavior.
Automation bias - Automation bias is a tendency to give automated recommendations undue weight when making decisions, including accepting an incorrect recommendation despite...
Automation Complacency Bias - Automation complacency bias concerns over-reliance on automated systems that weakens active checking and can leave people less prepared to perform or...
Automaton - An automaton is a mathematical model of a computing system whose behavior is described through states and transition rules, sometimes with additional memory.
Autonomic computing - Autonomic computing is an approach to building computing systems that manage aspects of their own operation according to human-defined goals and policies.
Autonomic networking - Autonomic networking is an approach in which network functions manage aspects of their own configuration, optimization, protection or recovery.
Autonomous agent - An autonomous agent is an AI agent that can pursue a goal over many steps without a person directing each step, deciding its own sequence of actions within...
Autonomy - Autonomy in an AI system is its ability to select and carry out actions toward a goal without a person directing every step, within a defined scope.
Autorater evaluation - Autorater evaluation uses an automated rating system, often a language model, to judge outputs against defined criteria or compare competing responses.
Autoregressive conditional duration - Autoregressive conditional duration, or ACD, is a time-series modeling framework for the positive waiting times between successive events.
Autoregressive Conditional Heteroskedasticity - Autoregressive conditional heteroskedasticity, usually abbreviated ARCH, is a statistical approach for modeling how the variability of a time-series error...
Autoregressive Distributed Lag - An autoregressive distributed lag model, or ARDL model, explains a time-series outcome using its own past values and current or past values of other variables.
Autoregressive flow - An autoregressive flow is a normalizing flow whose invertible transformations use an ordered dependence structure across coordinates.
Autoregressive Hidden Markov Model - An autoregressive hidden Markov model is a hidden Markov model in which each observation depends not only on the hidden state but also on the previous...
Autoregressive image model - An autoregressive image model represents an image as an ordered sequence and predicts each element using previously available elements.
Autoscaling, horizontal - Horizontal autoscaling automatically increases or decreases the number of running instances that share a workload.
Autoscaling, vertical - Vertical autoscaling automatically adjusts the resources assigned to an individual workload instance, such as its CPU or memory allocation.
Auxiliary - An auxiliary is a grammatical word that helps express distinctions such as tense, aspect, voice, or modality in a predicate.
Auxiliary Classifier GAN - An Auxiliary Classifier GAN, or AC-GAN, is a class-conditional generative adversarial network whose discriminator predicts both whether an example is real...
Auxiliary loss - An auxiliary loss is an extra loss term added to a model's training objective, alongside the main loss, to give additional learning signal and help the...
Auxiliary particle filter - An auxiliary particle filter is a sequential Monte Carlo method that uses the latest observation to help select which existing particles should produce the...
Auxiliary Tasks - Auxiliary tasks are extra learning tasks, related to the main one, that a model is trained on at the same time, to help it learn representations that...
Auxiliary variable Markov chain Monte Carlo - Auxiliary variable Markov chain Monte Carlo is a family of sampling methods that introduces additional variables to help explore a probability distribution.
Availability - Availability is the property of information or a service being accessible and usable by authorized users when needed, within an acceptable time.
Availability zone - An availability zone is a cloud provider's designated group of one or more datacenters within a region, designed as a separate failure boundary.
Average bitrate - Average bitrate is the total number of bits used or transferred divided by the elapsed duration, usually expressed in bits per second.
Average degree connectivity - Average degree connectivity describes the average degree of neighbors of nodes that share a particular degree.
Average neighbor degree - Average neighbor degree is the mean number of connections held by a node's immediate neighbors.
Average node degree - Average node degree is the arithmetic mean of the degrees of all nodes in a graph.
Average precision at k - Average precision at k, commonly written AP@k, evaluates how early relevant items appear within the first k positions of a ranked result list.
Average reward - Average reward is a reinforcement-learning objective that evaluates a policy by its long-run expected reward per time step.
Average treatment effect - The average treatment effect, or ATE, is the average difference between the outcome a defined population would experience under one intervention and the...
Average treatment effect on the treated - The average treatment effect on the treated, or ATT, is the average causal effect of an intervention among the units that actually received it.
Averaged one-dependence estimators - Averaged one-dependence estimators, or AODE, is a probabilistic classification method that averages a constrained collection of models allowing limited...
Axiom - An axiom is a statement accepted as a starting assumption within a formal theory or knowledge system.
Axis-aligned condition - An axis-aligned condition is a test in a decision tree that looks at one feature only, such as age is below 30 or temperature is above 25, splitting the...