THETA: A High-Efficiency Training Accelerator for DNNs With Triple-Side Sparsity Exploration.
Jinming LuJian HuangZhongfeng WangPublished in: IEEE Trans. Very Large Scale Integr. Syst. (2022)
Keyphrases
- high efficiency
- high accuracy
- real and synthetic datasets
- training set
- density based clustering
- arbitrary shape
- memory space
- online learning
- training process
- supervised learning
- training examples
- interactive exploration
- neural network
- parallel implementation
- serious games
- worst case
- upper bound
- reinforcement learning
- decision trees