Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks.
Torsten HoeflerDan AlistarhTal Ben-NunNikoli DrydenAlexandra PestePublished in: CoRR (2021)
Keyphrases
- deep learning
- efficient inference
- neural network
- structured prediction
- probabilistic inference
- unsupervised learning
- exact inference
- markov random field
- machine learning
- mental models
- conditional random fields
- approximate inference
- training set
- weakly supervised
- hidden variables
- pattern recognition
- markov networks
- graph structure
- supervised learning
- belief propagation
- back propagation
- artificial neural networks
- information retrieval
- maximum margin
- support vector
- pairwise
- belief networks
- multilayer perceptron
- latent variables
- training samples
- model selection
- graphical models