Results for "probability over text"

Inferring the agent’s internal state from noisy sensor data.

The shape of the loss function over parameter space.

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

Adjusting learning rate over training to improve convergence.

Shift in feature distribution over time.

System that independently pursues goals over time.

Number of steps considered in planning.

Equations governing how system states change over time.

When information from evaluation data improperly influences training, inflating reported performance.

Scalar summary of ROC; measures ranking ability, not calibration.

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

A proper scoring rule measuring squared error of predicted probabilities for binary outcomes.

Randomly zeroing activations during training to reduce co-adaptation and overfitting.

Predicts masked tokens in a sequence, enabling bidirectional context; often used for embeddings rather than generation.

Artificially created data used to train/test models; helpful for privacy and coverage, risky if unrealistic.

Scales logits before sampling; higher increases randomness/diversity, lower increases determinism.

Exponential of average negative log-likelihood; lower means better predictive fit, not necessarily better utility.

Strategy mapping states to actions.

A theoretical framework analyzing what classes of functions can be learned, how efficiently, and with what guarantees.

Probabilistic model for sequential data with latent states.

Expected return of taking action in a state.

Learns the score (∇ log p(x)) for generative sampling.

Autoencoder using probabilistic latent variables and KL regularization.

Predicting future values from past observations.

Identifying abrupt changes in data generation.

Measure of spread around the mean.

Optimization under uncertainty.

Assigning a role or identity to the model.

Sampling multiple outputs and selecting consensus.

Central log of AI-related risks.