State Space Search

Fuzzy Logic

A form of logic that handles approximate reasoning, allowing variables to have degrees of truth rather than strict binary true/false values.

Bayesian Reasoning

A statistical approach to AI that uses Bayes' theorem to update probability estimates as new evidence becomes available.

Heuristic Search

Problem-solving techniques that use practical rules of thumb to find satisfactory solutions when exhaustive search is impractical.

Constraint Satisfaction

A computational approach where problems are defined as a set of variables, domains, and constraints that must all be simultaneously satisfied.

Planning Algorithm

An AI algorithm that generates a sequence of actions to achieve a specified goal from an initial state.

Forward Chaining

An inference strategy that starts with known facts and applies rules to derive new conclusions until a goal is reached.

Backward Chaining

An inference strategy that starts with a goal and works backward through rules to determine what facts must be true.

Abductive Reasoning

A form of logical inference that seeks the simplest and most likely explanation for a set of observations.

Artificial intelligence algorithms processed locally on edge devices rather than in centralised cloud data centres.

A degradation phenomenon where AI models trained on AI-generated data progressively lose diversity and accuracy, converging toward a narrow distribution of outputs.

A measurement of how well a probability model predicts a sample, commonly used to evaluate language model performance.

Techniques for embedding imperceptible statistical patterns in AI-generated content to enable reliable detection and provenance tracking of synthetic outputs.

A graphical plot illustrating the diagnostic ability of a binary classifier as its discrimination threshold is varied.

A training paradigm where AI models are refined using human preference signals, aligning model outputs with human values and quality expectations through reward modelling.

A technique where a language model is given a small number of examples within the prompt to guide its response pattern.

Systematic errors in AI outputs that arise from biased training data, flawed assumptions, or prejudicial algorithm design.