Scale out for large minibatch SGD: Residual network training on ImageNet-1K with improved accuracy and reduced time to train.
Valeriu CodreanuDamian PodareanuVikram A. SaletorePublished in: CoRR (2017)
Keyphrases
- improved accuracy
- structural svms
- computer networks
- recurrent networks
- stochastic gradient descent
- supervised learning
- radial basis function network
- prediction accuracy
- complex networks
- wireless sensor networks
- network model
- peer to peer
- network structure
- network traffic
- linear svm
- training examples
- neural network structure