Results for "data distribution"

Methods to protect model/data during inference (e.g., trusted execution environments) from operators/attackers.

Learning only from current policy’s data.

Systematic error introduced by simplifying assumptions in a learning algorithm.

Detecting unauthorized model outputs or data leaks.

Estimating parameters by maximizing likelihood of observed data.

Neural networks that operate on graph-structured data by propagating information along edges.

Two-network setup where generator fools a discriminator.

Exact likelihood generative models using invertible transforms.

Attention between different modalities.

CNNs applied to time series.

End-to-end process for model training.

Centralized repository for curated features.

Running predictions on large datasets periodically.

Scaling law optimizing compute vs data.

Competitive advantage from proprietary models/data.

Model trained on its own outputs degrades quality.

Startup latency for services.

Storing results to reduce compute.

Software pipeline converting raw sensor data into structured representations.

Models estimating recidivism risk.

Learning physical parameters from data.

Finding mathematical equations from data.

Learning a function from input-output pairs (labeled data), optimizing performance on predicting outputs for unseen inputs.

Reusing knowledge from a source task/domain to improve learning on a target task/domain, typically via pretrained models.

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

One complete traversal of the training dataset during training.

A parameterized function composed of interconnected units organized in layers with nonlinear activations.

Networks using convolution operations with weight sharing and locality, effective for images and signals.

Networks with recurrent connections for sequences; largely supplanted by Transformers for many tasks.

Converting text into discrete units (tokens) for modeling; subword tokenizers balance vocabulary size and coverage.