Results for "meaning-based retrieval"

Sampling-based motion planner.

Learning by minimizing prediction error.

Acting to minimize surprise or free energy.

Software regulated as a medical device.

Deep learning system for protein structure prediction.

Learning only from current policy’s data.

Internal representation of the agent itself.

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

Training with a small labeled dataset plus a larger unlabeled dataset, leveraging assumptions like smoothness/cluster structure.

A continuous vector encoding of an item (word, image, user) such that semantic similarity corresponds to geometric closeness.

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

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

One complete traversal of the training dataset during training.

Methods to set starting weights to preserve signal/gradient scales across layers.

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

Mechanism that computes context-aware mixtures of representations; scales well and captures long-range dependencies.

Injects sequence order into Transformers, since attention alone is permutation-invariant.

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

A high-capacity language model trained on massive corpora, exhibiting broad generalization and emergent behaviors.

Maximum number of tokens the model can attend to in one forward pass; constrains long-document reasoning.

The text (and possibly other modalities) given to an LLM to condition its output behavior.

Letting an LLM call external functions/APIs to fetch data, compute, or take actions, improving reliability.

Model trained to predict human preferences (or utility) for candidate outputs; used in RLHF-style pipelines.

Controlled experiment comparing variants by random assignment to estimate causal effects of changes.

Ordering training samples from easier to harder to improve convergence or generalization.

Central system to store model versions, metadata, approvals, and deployment state.

Artificially created data used to train/test models; helpful for privacy and coverage, risky if unrealistic.

Search algorithm for generation that keeps top-k partial sequences; can improve likelihood but reduce diversity.

Raw model outputs before converting to probabilities; manipulated during decoding and calibration.

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