An energy-efficient deep learning processor with heterogeneous multi-core architecture for convolutional neural networks and recurrent neural networks.
Dongjoo ShinJinmook LeeJinsu LeeJuhyoung LeeHoi-Jun YooPublished in: COOL Chips (2017)
Keyphrases
- multi core architecture
- recurrent neural networks
- deep learning
- energy efficient
- convolutional neural networks
- wireless sensor networks
- energy consumption
- sensor networks
- unsupervised learning
- feed forward
- neural network
- artificial neural networks
- echo state networks
- mental models
- base station
- machine learning
- energy efficiency
- routing protocol
- multi core processors
- digital signal processor
- sensor nodes
- weakly supervised
- wireless networks
- co occurrence
- supervised learning
- decision making
- learning algorithm
- single instruction multiple data
- genetic algorithm