Exploiting Sparsity in Pruned Neural Networks to Optimize Large Model Training.
Siddharth SinghAbhinav BhatelePublished in: IPDPS (2023)
Keyphrases
- neural network
- computational model
- training process
- training algorithm
- objective function
- pattern recognition
- artificial neural networks
- prior knowledge
- probability distribution
- theoretical framework
- neural network is trained
- bp neural network
- statistical model
- mathematical model
- theoretical analysis
- probabilistic model
- active learning
- training set
- similarity measure