Results for "exposure analysis"

Differences between training and inference conditions.

Quantifying financial risk.

Attacks that infer whether specific records were in training data, or reconstruct sensitive training examples.

Methods to protect model/data during inference (e.g., trusted execution environments) from operators/attackers.

AI supporting legal research, drafting, and analysis.

AI predicting crime patterns (highly controversial).

Learning structure from unlabeled data, such as discovering groups, compressing representations, or modeling data distributions.

Graphs containing multiple node or edge types with different semantics.

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

Sequential data indexed by time.

Persistent directional movement over time.

Expected causal effect of a treatment.

Mathematical foundation for ML involving vector spaces, matrices, and linear transformations.

Vector whose direction remains unchanged under linear transformation.

Vectors with zero inner product; implies independence.

Measures joint variability between variables.

Privacy risk analysis under GDPR-like laws.

Stability proven via monotonic decrease of Lyapunov function.

Motion considering forces and mass.

Systems where failure causes physical harm.

AI-driven buying/selling of financial assets.

Predicts masked tokens in a sequence, enabling bidirectional context; often used for embeddings rather than generation.

An RNN variant using gates to mitigate vanishing gradients and capture longer context.

Crafting prompts to elicit desired behavior, often using role, structure, constraints, and examples.

A model that assigns probabilities to sequences of tokens; often trained by next-token prediction.

Techniques to understand model decisions (global or local), important in high-stakes and regulated settings.

Studying internal mechanisms or input influence on outputs (e.g., saliency maps, SHAP, attention analysis).

When some classes are rare, requiring reweighting, resampling, or specialized metrics.

Structured dataset documentation covering collection, composition, recommended uses, biases, and maintenance.

Logging hyperparameters, code versions, data snapshots, and results to reproduce and compare experiments.