Results for "function calling"

Constraining model outputs into a schema used to call external APIs/tools safely and deterministically.

A function measuring prediction error (and sometimes calibration), guiding gradient-based optimization.

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

The learned numeric values of a model adjusted during training to minimize a loss function.

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

The shape of the loss function over parameter space.

Neural networks can approximate any continuous function under certain conditions.

Sensitivity of a function to input perturbations.

Direction of steepest ascent of a function.

Stability proven via monotonic decrease of Lyapunov function.

Inferring reward function from observed behavior.

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

Nonlinear functions enabling networks to approximate complex mappings; ReLU variants dominate modern DL.

Expected cumulative reward from a state or state-action pair.

Expected return of taking action in a state.

Probability of data given parameters.