Disentangling the Gauss-Newton Method and Approximate Inference for Neural Networks.
Alexander ImmerPublished in: CoRR (2020)
Keyphrases
- approximate inference
- newton method
- neural network
- graphical models
- belief propagation
- probabilistic inference
- convergence analysis
- message passing
- gaussian process
- parameter estimation
- bayesian networks
- latent variables
- conditional random fields
- dynamic bayesian networks
- artificial neural networks
- graph cuts
- probabilistic model
- multilayer perceptron
- back propagation
- em algorithm
- information extraction