On the Convergence of Gradient Descent Training for Two-layer ReLU-networks in the Mean Field Regime.
Stephan WojtowytschPublished in: CoRR (2020)
Keyphrases
- training process
- markov random field
- social networks
- training set
- echo state networks
- multi layer
- network structure
- cost function
- closed form
- belief networks
- recurrent networks
- statistical mechanics
- training samples
- hidden markov models
- complex networks
- convergence rate
- artificial neural networks
- training algorithm
- global convergence
- neural network