Results for "continual learning"

Humans assist or override autonomous behavior.

Robots learning via exploration and growth.

Inferring and aligning with human preferences.

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

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

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

Designing input features to expose useful structure (e.g., ratios, lags, aggregations), often crucial outside deep learning.

Human or automated process of assigning targets; quality, consistency, and guidelines matter heavily.

System design where humans validate or guide model outputs, especially for high-stakes decisions.

A measure of a model class’s expressive capacity based on its ability to shatter datasets.

Systematic error introduced by simplifying assumptions in a learning algorithm.

Strategy mapping states to actions.

Combines value estimation (critic) with policy learning (actor).

Balancing learning new behaviors vs exploiting known rewards.

Continuous cycle of observation, reasoning, action, and feedback.

Combining simulation and real-world data.

RL without explicit dynamics model.

Learned model of environment dynamics.

Learning without catastrophic forgetting.

Deep learning system for protein structure prediction.

AI limited to specific domains.

A measurable property or attribute used as model input (raw or engineered), such as age, pixel intensity, or token ID.

A function measuring prediction error (and sometimes calibration), guiding gradient-based optimization.

Automated testing and deployment processes for models and data workflows, extending DevOps to ML artifacts.

Practices for operationalizing ML: versioning, CI/CD, monitoring, retraining, and reliable production management.

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

Hidden behavior activated by specific triggers, causing targeted mispredictions or undesired outputs.

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

All possible configurations an agent may encounter.

Models evaluating and improving their own outputs.