Results for "theory discovery"
AI-assisted review of legal documents.
AI discovering new compounds/materials.
AI selecting next experiments.
Retrieval based on embedding similarity rather than keyword overlap, capturing paraphrases and related concepts.
Requirement to preserve relevant data.
AI applied to scientific problems.
AI proposing scientific hypotheses.
Designing systems where rational agents behave as desired.
Mathematical framework for controlling dynamic systems.
Designing efficient marketplaces.
A theoretical framework analyzing what classes of functions can be learned, how efficiently, and with what guarantees.
Research ensuring AI remains safe.
Feature attribution method grounded in cooperative game theory for explaining predictions in tabular settings.
Multiple agents interacting cooperatively or competitively.
Tendency for agents to pursue resources regardless of final goal.
Willingness of system to accept correction or shutdown.
Storing results to reduce compute.
Stability proven via monotonic decrease of Lyapunov function.
Control that remains stable under model uncertainty.
Optimizing continuous action sequences.
Quantifying financial risk.
No agent benefits from unilateral deviation.
Some agents know more than others.
Ensuring AI allows shutdown.
Risk threatening humanity’s survival.
A subfield of AI where models learn patterns from data to make predictions or decisions, improving with experience rather than explicit rule-coding.
A branch of ML using multi-layer neural networks to learn hierarchical representations, often excelling in vision, speech, and language.
Learning structure from unlabeled data, such as discovering groups, compressing representations, or modeling data distributions.
Training with a small labeled dataset plus a larger unlabeled dataset, leveraging assumptions like smoothness/cluster structure.
Minimizing average loss on training data; can overfit when data is limited or biased.