RSO: A Gradient Free Sampling Based Approach For Training Deep Neural Networks.
Rohun TripathiBharat SinghPublished in: CoRR (2020)
Keyphrases
- neural network
- training process
- training algorithm
- feedforward neural networks
- backpropagation algorithm
- feed forward neural networks
- artificial neural networks
- multi layer perceptron
- back propagation
- training patterns
- neural network structure
- edge detection
- neural network training
- genetic algorithm
- training phase
- error back propagation
- fuzzy systems
- random sampling
- multilayer perceptron
- monte carlo
- training set
- deep architectures
- multi layer
- self organizing maps
- hidden layer
- data sets
- sampling methods
- deep learning
- sample size
- test set
- training examples
- semi supervised
- pattern recognition
- training data
- weighted sums