Convergence of SGD for Training Neural Networks with Sliced Wasserstein Losses.
Eloi TanguyPublished in: CoRR (2023)
Keyphrases
- neural network
- training process
- training algorithm
- feedforward neural networks
- feed forward neural networks
- stochastic gradient descent
- multi layer perceptron
- back propagation
- training speed
- backpropagation algorithm
- error back propagation
- artificial neural networks
- pattern recognition
- online learning
- weight update
- recurrent networks
- feed forward
- multilayer perceptron
- recurrent neural networks
- neural network training
- support vector machine
- activation function
- neural network structure
- multi layer
- convergence rate
- neural network model
- training data
- learning algorithm
- genetic algorithm