Results for "data → model"

Of predicted positives, the fraction that are truly positive; sensitive to false positives.

Of true positives, the fraction correctly identified; sensitive to false negatives.

Of true negatives, the fraction correctly identified.

Scalar summary of ROC; measures ranking ability, not calibration.

Average of squared residuals; common regression objective.

Number of samples per gradient update; impacts compute efficiency, generalization, and stability.

Methods to set starting weights to preserve signal/gradient scales across layers.

Architecture based on self-attention and feedforward layers; foundation of modern LLMs and many multimodal models.

Breaking documents into pieces for retrieval; chunk size/overlap strongly affect RAG quality.

Framework for reasoning about cause-effect relationships beyond correlation, often using structural assumptions and experiments.

Scales logits before sampling; higher increases randomness/diversity, lower increases determinism.

Samples from the k highest-probability tokens to limit unlikely outputs.

A dataset + metric suite for comparing models; can be gamed or misaligned with real-world goals.

A discipline ensuring AI systems are fair, safe, transparent, privacy-preserving, and accountable throughout lifecycle.

Reduction in uncertainty achieved by observing a variable; used in decision trees and active learning.

Generating speech audio from text, with control over prosody, speaker identity, and style.

Measures how one probability distribution diverges from another.

Optimization using curvature information; often expensive at scale.

Matrix of second derivatives describing local curvature of loss.

Tradeoffs between many layers vs many neurons per layer.

Models evaluating and improving their own outputs.

Pixel-level separation of individual object instances.

Pixel-wise classification of image regions.

Transformer applied to image patches.

Recovering 3D structure from images.

Detects trigger phrases in audio streams.

Generates audio waveforms from spectrograms.

Optimal estimator for linear dynamic systems.

Agent reasoning about future outcomes.

Measure of vector magnitude; used in regularization and optimization.