A High Energy Efficient Reconfigurable Hybrid Neural Network Processor for Deep Learning Applications.
Shouyi YinPeng OuyangShibin TangFengbin TuXiudong LiShixuan ZhengTianyi LuJiangyuan GuLeibo LiuShaojun WeiPublished in: IEEE J. Solid State Circuits (2018)
Keyphrases
- energy efficient
- deep learning
- hybrid neural network
- wireless sensor networks
- multi core architecture
- energy consumption
- sensor networks
- unsupervised learning
- unsupervised feature learning
- high speed
- mental models
- base station
- low cost
- weakly supervised
- routing protocol
- energy efficiency
- neural network
- machine learning
- multiscale
- sensor nodes
- principal component analysis
- training data