E-PUR: An Energy-Efficient Processing Unit for Recurrent Neural Networks.
Franyell SilfaGem DotJosé-María ArnauAntonio GonzálezPublished in: CoRR (2017)
Keyphrases
- recurrent neural networks
- processing units
- wireless sensor networks
- computing systems
- parallel computing
- neural network
- parallel processing
- echo state networks
- feed forward
- sensor networks
- recurrent networks
- reservoir computing
- artificial neural networks
- nonlinear dynamic systems
- energy efficiency
- neural model
- cascade correlation
- multiple types
- energy consumption
- expert systems
- information systems
- real world