TSUNAMI: Triple Sparsity-Aware Ultra Energy-Efficient Neural Network Training Accelerator With Multi-Modal Iterative Pruning.
Sangyeob KimJuhyoung LeeSanghoon KangDonghyeon HanWooyoung JoHoi-Jun YooPublished in: IEEE Trans. Circuits Syst. I Regul. Pap. (2022)
Keyphrases
- multi modal
- energy efficient
- neural network training
- wireless sensor networks
- high dimensional
- training algorithm
- neural network
- energy consumption
- sensor networks
- optimization method
- base station
- sensor nodes
- multi modality
- energy efficiency
- high speed
- search space
- mobile phone
- routing protocol
- particle swarm optimisation
- uni modal
- data transmission
- routing algorithm
- back propagation
- training process
- machine learning