Improving Hardware Efficiency of a Sparse Training Accelerator by Restructuring a Reduction Network.
Banseok ShinSehun ParkJaeha KungPublished in: NEWCAS (2023)
Keyphrases
- real time
- recurrent networks
- hardware and software
- low cost
- training set
- computer networks
- network structure
- training phase
- computer systems
- network architecture
- training algorithm
- network model
- training examples
- peer to peer
- mobile devices
- high dimensional
- abstraction layer
- parallel computing
- field programmable gate array
- application level
- network traffic
- data flow
- communication networks
- signal processing
- training data
- image processing
- learning algorithm
- neural network