Results for "Bayesian update"

Bayesian parameter estimation using the mode of the posterior distribution.

Early signals disproportionately influence outcomes.

Updating beliefs about parameters using observed evidence and prior distributions.

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

Number of samples per gradient update; impacts compute efficiency, generalization, and stability.

Monte Carlo method for state estimation.

Acting to minimize surprise or free energy.

Identifying abrupt changes in data generation.

Updated belief after observing data.

Belief before observing data.

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

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

A gradient method using random minibatches for efficient training on large datasets.

Popular optimizer combining momentum and per-parameter adaptive step sizes via first/second moment estimates.

Controls the size of parameter updates; too high diverges, too low trains slowly or gets stuck.

Continuous cycle of observation, reasoning, action, and feedback.

Expected return of taking action in a state.

Recovering training data from gradients.

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

GNN framework where nodes iteratively exchange and aggregate messages from neighbors.

Simultaneous Localization and Mapping for robotics.

Agents communicate via shared state.

Matrix of curvature information.

Internal representation of the agent itself.

Configuration choices not learned directly (or not typically learned) that govern training or architecture.

Selecting the most informative samples to label (e.g., uncertainty sampling) to reduce labeling cost.

Graphical model expressing factorization of a probability distribution.

Autoencoder using probabilistic latent variables and KL regularization.

Optimal estimator for linear dynamic systems.

Describes likelihoods of random variable outcomes.