Results for "full pass through data"

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

Training one model on multiple tasks simultaneously to improve generalization through shared structure.

Gradients shrink through layers, slowing learning in early layers; mitigated by ReLU, residuals, normalization.

AI systems that perceive and act in the physical world through sensors and actuators.

Learning structure from unlabeled data, such as discovering groups, compressing representations, or modeling data distributions.

Minimizing average loss on training data; can overfit when data is limited or biased.

When a model fits noise/idiosyncrasies of training data and performs poorly on unseen data.

Training across many devices/silos without centralizing raw data; aggregates updates, not data.

Protecting data during network transfer and while stored; essential for ML pipelines handling sensitive data.

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

Expanding training data via transformations (flips, noise, paraphrases) to improve robustness.

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

Processes and controls for data quality, access, lineage, retention, and compliance across the AI lifecycle.

Tracking where data came from and how it was transformed; key for debugging and compliance.

Maliciously inserting or altering training data to implant backdoors or degrade performance.

Increasing performance via more data.

The field of building systems that perform tasks associated with human intelligence—perception, reasoning, language, planning, and decision-making—via algori...

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.

Learning from data by constructing “pseudo-labels” (e.g., next-token prediction, masked modeling) without manual annotation.

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

Methods that learn training procedures or initializations so models can adapt quickly to new tasks with little data.

A mismatch between training and deployment data distributions that can degrade model performance.

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

When a model cannot capture underlying structure, performing poorly on both training and test data.

A conceptual framework describing error as the sum of systematic error (bias) and sensitivity to data (variance).

How well a model performs on new data drawn from the same (or similar) distribution as training.

Separating data into training (fit), validation (tune), and test (final estimate) to avoid leakage and optimism bias.

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

Updating a pretrained model’s weights on task-specific data to improve performance or adapt style/behavior.