Convergence of SGD for Training Neural Networks with Sliced Wasserstein Losses.
Eloi TanguyPublished in: Trans. Mach. Learn. Res. (2023)
Keyphrases
- neural network
- training process
- training algorithm
- stochastic gradient descent
- feedforward neural networks
- backpropagation algorithm
- feed forward neural networks
- multi layer perceptron
- back propagation
- artificial neural networks
- update rule
- training set
- training speed
- error back propagation
- neural network training
- training samples
- pattern recognition
- pointwise
- training examples
- fuzzy logic
- support vector machine
- neural network model
- training phase
- online training
- weight update
- test set
- radial basis function network
- active learning
- training data
- genetic algorithm