OmniDRL: An Energy-Efficient Mobile Deep Reinforcement Learning Accelerators with Dual-mode Weight Compression and Direct Processing of Compressed Data.
Juhyoung LeeSangyeob KimJi-Hoon KimSangjin KimWooyoung JoDonghyeon HanHoi-Jun YooPublished in: HCS (2021)
Keyphrases
- compressed data
- data compression
- reinforcement learning
- compression ratio
- raw data
- data structure
- lossless compression
- compressed images
- run length encoding
- original data
- data cube
- main memory
- reconstructed image
- image compression
- bitstream
- compression algorithm
- database
- nearest neighbor
- databases
- data sets
- visual quality
- image reconstruction
- image quality
- multi dimensional
- dimensionality reduction
- quadtree
- wireless sensor networks