Category · 15 terms
Foundations & History
defined clearly.
The ideas, debates, and milestones that shape modern AI — from symbolic reasoning to deep learning.
A* Search (A-Star)
A heuristic search algorithm that finds the shortest path between nodes by combining actual cost-so-far with an estimated cost-to-goal.
Artificial General Intelligence (AGI)
A hypothetical AI system that matches or exceeds human capability across the full range of intellectual tasks, not just narrow domains.
Artificial Intelligence (AI)
The science and engineering of building machines that perform tasks associated with human intelligence — the umbrella discipline under which ML, NLP, CV, and robotics live.
Artificial Narrow Intelligence (ANI)
AI specialised for a single task or narrow domain — image classification, fraud detection, language translation. Every system in production today is ANI.
Bayesian Inference
A statistical approach that updates beliefs about hypotheses as new evidence arrives, using Bayes' theorem.
Cognitive Science
The interdisciplinary study of the mind — psychology, linguistics, neuroscience, philosophy, computer science, and anthropology; one of AI's parent disciplines.
Connectionism
The view that cognition emerges from the interactions of many simple connected units — the intellectual ancestor of modern neural networks and deep learning.
Cybernetics
The transdisciplinary study of regulatory systems — feedback, control, and communication in animals, machines, and organisations. The intellectual forerunner of AI.
Expert System
A rule-based AI system that captures domain knowledge from human experts and applies it through a logical inference engine.
Game Theory
The mathematical study of strategic decision-making between rational agents. Foundational to multi-agent AI, mechanism design, and adversarial ML.
Heuristic
A rule of thumb or approximation that gives good-enough answers with bounded effort, even if not optimal — the unglamorous backbone of production AI.
Markov Chain
A stochastic process where the next state depends only on the current state — the mathematical foundation of many ML techniques and the original language-model idea.
Optimization
The mathematical discipline of finding parameter values that minimise or maximise an objective — the engine under every trained machine-learning model.
Symbolic AI (GOFAI)
The pre-deep-learning approach of encoding knowledge as explicit logical rules and symbols. Often called "Good Old-Fashioned AI."
Turing Test
Alan Turing's 1950 thought experiment: if a human judge cannot reliably distinguish a machine's text replies from a human's, the machine demonstrates intelligent behaviour.