DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks.
Yonggan FuHaichuan YangJiayi YuanMeng LiCheng WanRaghuraman KrishnamoorthiVikas ChandraYingyan LinPublished in: CoRR (2022)
Keyphrases
- neural network
- pattern recognition
- artificial neural networks
- hardware and software
- data compression
- real time
- low cost
- compression ratio
- real world
- genetic algorithm
- learning algorithm
- feed forward
- adaboost algorithm
- activation function
- ensemble methods
- recurrent neural networks
- multilayer perceptron
- compression algorithm
- neural network model
- back propagation
- face detection
- computer systems
- computational complexity