, 3.08 Gop/s/mW @ 1.2 mW Accelerator for Near-Sensor Recurrent Neural Network Inference.
Francesco ContiLukas CavigelliGianna PaulinIgor SusmeljLuca BeniniPublished in: CoRR (2017)
Keyphrases
- recurrent neural networks
- power consumption
- feed forward
- recurrent networks
- complex valued
- neural network
- power supply
- long short term memory
- power plant
- feedforward neural networks
- artificial neural networks
- wind turbine
- bayesian networks
- echo state networks
- reservoir computing
- real time
- hidden layer
- parallel implementation
- neural model