Results for "data-driven"

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

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

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

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

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

The internal space where learned representations live; operations here often correlate with semantics or generative factors.

Empirical laws linking model size, data, compute to performance.

Recovering training data from gradients.

Generative model that learns to reverse a gradual noise process.

Diffusion model trained to remove noise step by step.

Diffusion performed in latent space for efficiency.

Sequential data indexed by time.

Artificial sensor data generated in simulation.

Combining simulation and real-world data.

A formal privacy framework ensuring outputs do not reveal much about any single individual’s data contribution.

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

A branch of ML using multi-layer neural networks to learn hierarchical representations, often excelling in vision, speech, and language.

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

Automatically learning useful internal features (latent variables) that capture salient structure for downstream tasks.

Forcing predictable formats for downstream systems; reduces parsing errors and supports validation/guardrails.

Learning from data generated by a different policy.

Models that learn to generate samples resembling training data.

Model that compresses input into latent space and reconstructs it.

Shift in model outputs.

Probability of data given parameters.

Updated belief after observing data.

Enables external computation or lookup.

Running models locally.

Requirement to preserve relevant data.

Trend reversal when data is aggregated improperly.