Overview
Architectures that enable AI agents to store, retrieve, and reason over information from past interactions, providing continuity and personalisation across conversations.
Cross-References(1)
More in Artificial Intelligence
AI Fairness
Safety & GovernanceThe principle of ensuring AI systems make equitable decisions without discriminating against any group based on protected attributes.
AI Red Teaming
Safety & GovernanceThe systematic adversarial testing of AI systems to identify vulnerabilities, failure modes, harmful outputs, and safety risks before deployment.
Confusion Matrix
Evaluation & MetricsA table used to evaluate classification model performance by comparing predicted classifications against actual classifications.
TinyML
Evaluation & MetricsMachine learning techniques optimised to run on microcontrollers and extremely resource-constrained embedded devices.
Neural Architecture Search
Models & ArchitectureAn automated technique for designing optimal neural network architectures using search algorithms.
Model Collapse
Models & ArchitectureA degradation phenomenon where AI models trained on AI-generated data progressively lose diversity and accuracy, converging toward a narrow distribution of outputs.
Few-Shot Learning
Prompting & InteractionA machine learning approach where models learn to perform tasks from only a small number of labelled examples, often achieved through in-context learning in large language models.
Tool Use in AI
Prompting & InteractionThe capability of AI agents to invoke external tools, APIs, databases, and software applications to accomplish tasks beyond the model's intrinsic knowledge and abilities.