Ising Dropout with Node Grouping for Training and Compression of Deep Neural Networks.
Hojjat SalehinejadZijian WangShahrokh ValaeePublished in: GlobalSIP (2019)
Keyphrases
- neural network
- training process
- training algorithm
- artificial neural networks
- backpropagation algorithm
- multi layer perceptron
- feed forward neural networks
- back propagation
- neural network training
- pattern recognition
- data compression
- deep architectures
- neural network model
- feedforward neural networks
- radial basis function network
- test set
- image compression
- error back propagation
- recurrent networks
- training set
- compression algorithm
- fuzzy logic
- upper bound
- tree structure
- perceptual grouping
- graph structure
- multilayer perceptron
- self organizing maps
- training examples
- training samples
- markov random field
- multiresolution
- support vector
- genetic algorithm
- machine learning