Results for "data → model"

A hidden variable influences both cause and effect, biasing naive estimates of causal impact.

Hardware resources used for training/inference; constrained by memory bandwidth, FLOPs, and parallelism.

Mechanisms for retaining context across turns/sessions: scratchpads, vector memories, structured stores.

Coordinating tools, models, and steps (retrieval, calls, validation) to deliver reliable end-to-end behavior.

AI focused on interpreting images/video: classification, detection, segmentation, tracking, and 3D understanding.

A measure of randomness or uncertainty in a probability distribution.

AI subfield dealing with understanding and generating human language, including syntax, semantics, and pragmatics.

Variability introduced by minibatch sampling during SGD.

A wide basin often correlated with better generalization.

Categorizing AI applications by impact and regulatory risk.

Combining signals from multiple modalities.

Simultaneous Localization and Mapping for robotics.

Repeating temporal patterns.

Set of vectors closed under addition and scalar multiplication.

Vector whose direction remains unchanged under linear transformation.

Measures similarity and projection between vectors.

Sensitivity of a function to input perturbations.

Eliminating variables by integrating over them.

Optimization under uncertainty.

European regulation classifying AI systems by risk.

AI used in sensitive domains requiring compliance.

Requirement to inform users about AI use.

Process for managing AI failures.

AI used without governance approval.

Limiting inference usage.

Dynamic resource allocation.

Internal sensing of joint positions, velocities, and forces.

Control using real-time sensor feedback.

Learning action mapping directly from demonstrations.

Detecting and avoiding obstacles.