HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise.
Souvik KunduMassoud PedramPeter A. BeerelPublished in: ICCV (2021)
Keyphrases
- energy efficient
- spiking neural networks
- training algorithm
- wireless sensor networks
- energy consumption
- sensor networks
- nearest neighbor
- input data
- training process
- training set
- neural network
- back propagation
- base station
- multi core architecture
- spiking neurons
- routing protocol
- biologically inspired
- routing algorithm
- feed forward
- sensor nodes
- biologically plausible
- learning rate
- feed forward neural networks
- sensor data
- expert systems
- real time