Results for "compute-data-performance"

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

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

Shift in feature distribution over time.

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

A robust evaluation technique that trains/evaluates across multiple splits to estimate performance variability.

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

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

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

Systematic review of model/data processes to ensure performance, fairness, security, and policy compliance.

Logging hyperparameters, code versions, data snapshots, and results to reproduce and compare experiments.

End-to-end process for model training.

A table summarizing classification outcomes, foundational for metrics like precision, recall, specificity.

Harmonic mean of precision and recall; useful when balancing false positives/negatives matters.

Often more informative than ROC on imbalanced datasets; focuses on positive class performance.

Guaranteed response times.

Control that remains stable under model uncertainty.

Tradeoff between safety and performance.

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

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

Combining simulation and real-world data.

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

Capabilities that appear only beyond certain model sizes.

Privacy risk analysis under GDPR-like laws.

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

Enables external computation or lookup.

Running models locally.

Halting training when validation performance stops improving to reduce overfitting.

Standardized documentation describing intended use, performance, limitations, data, and ethical considerations.

A broader capability to infer internal system state from telemetry, crucial for AI services and agents.

Exponential of average negative log-likelihood; lower means better predictive fit, not necessarily better utility.