Results for "vector search"

Finding mathematical equations from data.

Fast approximation of costly simulations.

Learning a function from input-output pairs (labeled data), optimizing performance on predicting outputs for unseen inputs.

A structured collection of examples used to train/evaluate models; quality, bias, and coverage often dominate outcomes.

A parameterized mapping from inputs to outputs; includes architecture + learned parameters.

A parameterized function composed of interconnected units organized in layers with nonlinear activations.

Gradients grow too large, causing divergence; mitigated by clipping, normalization, careful init.

Limiting gradient magnitude to prevent exploding gradients.

Networks with recurrent connections for sequences; largely supplanted by Transformers for many tasks.

Matrix of second derivatives describing local curvature of loss.

A narrow hidden layer forcing compact representations.

Low-latency prediction per request.

Attention between different modalities.

Models whose weights are publicly available.

Running predictions on large datasets periodically.

Measures similarity and projection between vectors.

Number of linearly independent rows or columns.

Visualization of optimization landscape.

Algorithm computing control actions.

Finding control policies minimizing cumulative cost.

Optimal control for linear systems with quadratic cost.

Study of motion without considering forces.

Detecting and avoiding obstacles.

Interpreting human gestures.

Controlling robots via language.

Automated assistance identifying disease indicators.

AI discovering new compounds/materials.

AI limited to specific domains.

Internal representation of the agent itself.

The field of building systems that perform tasks associated with human intelligence—perception, reasoning, language, planning, and decision-making—via algori...