Results for "regression loss"

Finding mathematical equations from data.

Penalizes confident wrong predictions heavily; standard for classification and language modeling.

The shape of the loss function over parameter space.

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

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

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

Iterative method that updates parameters in the direction of negative gradient to minimize loss.

Measures divergence between true and predicted probability distributions.

Average of squared residuals; common regression objective.

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

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

Visualization of optimization landscape.

Assigning labels per pixel (semantic) or per instance (instance segmentation) to map object boundaries.

Maximum expected loss under normal conditions.

Lowest possible loss.

The degree to which predicted probabilities match true frequencies (e.g., 0.8 means ~80% correct).

Local surrogate explanation method approximating model behavior near a specific input.

Uses an exponential moving average of gradients to speed convergence and reduce oscillation.

Halting training when validation performance stops improving to reduce overfitting.

A narrow minimum often associated with poorer generalization.

A wide basin often correlated with better generalization.

Matrix of second derivatives describing local curvature of loss.

Two-network setup where generator fools a discriminator.

Pixel-wise classification of image regions.

Minimum relative to nearby points.

Applying learned patterns incorrectly.

Loss of old knowledge when learning new tasks.

Learning policies from expert demonstrations.

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

A parameterized mapping from inputs to outputs; includes architecture + learned parameters.