An Energy-Efficient Accelerator with Relative- Indexing Memory for Sparse Compressed Convolutional Neural Network.
I-Chen WuPo-Tsang HuangChin-Yang LoWei HwangPublished in: AICAS (2019)
Keyphrases
- convolutional neural network
- face detection
- compute intensive
- hash table
- information retrieval
- data structure
- compressed data
- sparse data
- indexing method
- sensor networks
- energy efficient
- sparse representation
- data compression
- memory requirements
- main memory
- wireless sensor networks
- database
- machine learning
- random access
- compressed text
- indexing scheme
- compressed domain
- content based retrieval
- high dimensional
- object recognition
- string matching
- memory usage
- multimedia databases
- energy consumption
- object detection