On the rate of convergence of fully connected very deep neural network regression estimates.
Michael KohlerSophie LangerPublished in: CoRR (2019)
Keyphrases
- fully connected
- neural network
- activation function
- conditional random fields
- regression model
- neural network model
- back propagation
- network architecture
- feed forward
- artificial neural networks
- scale free
- recurrent neural networks
- convergence rate
- neural nets
- bp neural network
- fuzzy logic
- fault diagnosis
- convergence speed
- hidden layer
- prediction model
- prior knowledge
- support vector
- social network analysis
- markov random field
- information extraction
- regression problems