IM3A: Boosting Deep Neural Network Efficiency via In-Memory Addressing-Assisted Acceleration.
Fangxin LiuWenbo ZhaoZongwu WangTao YangLi JiangPublished in: ACM Great Lakes Symposium on VLSI (2021)
Keyphrases
- neural network
- back propagation
- learning algorithm
- pattern recognition
- memory usage
- associative memory
- auto associative
- computational complexity
- artificial neural networks
- neural network model
- genetic algorithm
- highly efficient
- bp neural network
- multilayer perceptron
- memory requirements
- feature selection
- cost sensitive
- prediction model
- feed forward
- ensemble learning
- semi supervised
- fuzzy neural network
- active learning
- memory space