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: CoRR (2021)
Keyphrases
- energy efficient
- spiking neural networks
- training algorithm
- wireless sensor networks
- energy consumption
- sensor networks
- energy efficiency
- input data
- base station
- biologically inspired
- back propagation
- training process
- neural network
- nearest neighbor
- routing protocol
- multi core architecture
- biologically plausible
- sensor nodes
- multi modal
- spiking neurons
- real time
- learning rate
- routing algorithm
- data transmission
- learning algorithm