Results for "dynamics learning"

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.

Strategy mapping states to actions.

Systematic error introduced by simplifying assumptions in a learning algorithm.

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

Balancing learning new behaviors vs exploiting known rewards.

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

Loss of old knowledge when learning new tasks.

Combining simulation and real-world data.

Learning without catastrophic forgetting.

Deep learning system for protein structure prediction.

AI limited to specific domains.

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

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.

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

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

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

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.

All possible configurations an agent may encounter.

Expected return of taking action in a state.

Models evaluating and improving their own outputs.

Probabilistic energy-based neural network with hidden variables.

Simplified Boltzmann Machine with bipartite structure.

Increasing performance via more data.

Visualization of optimization landscape.