Towards Understanding the Condensation of Two-layer Neural Networks at Initial Training.
Zhi-Qin John XuHanxu ZhouTao LuoYaoyu ZhangPublished in: CoRR (2021)
Keyphrases
- neural network
- training process
- multi layer
- training algorithm
- feedforward neural networks
- multi layer perceptron
- error back propagation
- neural network training
- feed forward neural networks
- back propagation
- pattern recognition
- artificial neural networks
- training phase
- single layer
- neural network structure
- recurrent neural networks
- recurrent networks
- training set
- activation function
- e learning
- particle filter
- backpropagation algorithm
- application layer
- radial basis function network
- initial set
- deeper understanding
- supervised learning
- text classification
- neural nets
- fault diagnosis
- training examples