Results for "changing target relationship"

Reusing knowledge from a source task/domain to improve learning on a target task/domain, typically via pretrained models.

Changing speaker characteristics while preserving content.

Sampling from easier distribution with reweighting.

Shift in model outputs.

Learning only from current policy’s data.

When information from evaluation data improperly influences training, inflating reported performance.

The relationship between inputs and outputs changes over time, requiring monitoring and model updates.

System that independently pursues goals over time.

Learning where data arrives sequentially and the model updates continuously, often under changing distributions.

Decomposing goals into sub-tasks.

No agent benefits from unilateral deviation.

Normalized covariance.

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

A scalar measure optimized during training, typically expected loss over data, sometimes with regularization terms.

Reconstructing a model or its capabilities via API queries or leaked artifacts.

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

Gradually increasing learning rate at training start to avoid divergence.

Learning from data generated by a different policy.

Generator produces limited variety of outputs.

Train/test environment mismatch.

Fundamental recursive relationship defining optimal value functions.

Classical statistical time-series model.

A subfield of AI where models learn patterns from data to make predictions or decisions, improving with experience rather than explicit rule-coding.

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

A branch of ML using multi-layer neural networks to learn hierarchical representations, often excelling in vision, speech, and language.

Time from request to response; critical for real-time inference and UX.

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

How many requests or tokens can be processed per unit time; affects scalability and cost.

Observing model inputs/outputs, latency, cost, and quality over time to catch regressions and drift.

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