DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks.
Yonggan FuHaichuan YangJiayi YuanMeng LiCheng WanRaghuraman KrishnamoorthiVikas ChandraYingyan LinPublished in: ICML (2022)
Keyphrases
- neural network
- real time
- hardware and software
- low cost
- fuzzy logic
- artificial neural networks
- high efficiency
- recurrent neural networks
- real world
- genetic algorithm
- compression ratio
- neural nets
- vlsi implementation
- hardware architecture
- combining multiple
- computing systems
- highly efficient
- semi supervised
- real life
- image processing
- feature selection
- data sets