Results for "vector representation"
Matrix of second derivatives describing local curvature of loss.
A narrow hidden layer forcing compact representations.
Attention between different modalities.
Low-latency prediction per request.
Running predictions on large datasets periodically.
Models whose weights are publicly available.
Measures similarity and projection between vectors.
Number of linearly independent rows or columns.
Direction of steepest ascent of a function.
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.
Learning from data by constructing “pseudo-labels” (e.g., next-token prediction, masked modeling) without manual annotation.
When a model cannot capture underlying structure, performing poorly on both training and test data.
A table summarizing classification outcomes, foundational for metrics like precision, recall, specificity.
Often more informative than ROC on imbalanced datasets; focuses on positive class performance.
Plots true positive rate vs false positive rate across thresholds; summarizes separability.
Converting text into discrete units (tokens) for modeling; subword tokenizers balance vocabulary size and coverage.
Constraining outputs to retrieved or provided sources, often with citation, to improve factual reliability.
Tracking where data came from and how it was transformed; key for debugging and compliance.
Methods for breaking goals into steps; can be classical (A*, STRIPS) or LLM-driven with tool calls.
Forcing predictable formats for downstream systems; reduces parsing errors and supports validation/guardrails.
Assigning labels per pixel (semantic) or per instance (instance segmentation) to map object boundaries.