Results for "sensitivity to data"

Variability introduced by minibatch sampling during SGD.

A wide basin often correlated with better generalization.

A narrow hidden layer forcing compact representations.

The range of functions a model can represent.

Allows model to attend to information from different subspaces simultaneously.

Encodes token position explicitly, often via sinusoids.

Models trained to decide when to call tools.

Logged record of model inputs, outputs, and decisions.

Compromising AI systems via libraries, models, or datasets.

Graphs containing multiple node or edge types with different semantics.

Extension of convolution to graph domains using adjacency structure.

Controls amount of noise added at each diffusion step.

Combining signals from multiple modalities.

Simultaneous Localization and Mapping for robotics.

Predicting future values from past observations.

Models time evolution via hidden states.

Monte Carlo method for state estimation.

Repeating temporal patterns.

Low-latency prediction per request.

Increasing model capacity via compute.

Using production outcomes to improve models.

Models accessible only via service APIs.

Set of vectors closed under addition and scalar multiplication.

Vector whose direction remains unchanged under linear transformation.

Measures similarity and projection between vectors.

Describes likelihoods of random variable outcomes.

Measure of spread around the mean.

Normalized covariance.

Eliminating variables by integrating over them.

Optimization under uncertainty.