Search Results for author:
Found 6 papers, 3 papers with code
One Timestep is All You Need: Training Spiking Neural Networks with Ultra Low Latency
We achieve top-1 accuracy of 93. 05%, 70. 15% and 67. 71% on CIFAR-10, CIFAR-100 and ImageNet, respectively using VGG16, with just 1 timestep.
DIET-SNN: A Low-Latency Spiking Neural Network with Direct Input Encoding & Leakage and Threshold Optimization
The trained membrane leak controls the flow of input information and attenuates irrelevant inputs to increase the activation sparsity in the convolutional and linear layers of the network.
DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networks
The trained membrane leak controls the flow of input information and attenuates irrelevant inputs to increase the activation sparsity in the convolutional and dense layers of the network.
Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation
We propose a hybrid training methodology: 1) take a converted SNN and use its weights and thresholds as an initialization step for spike-based backpropagation, and 2) perform incremental spike-timing dependent backpropagation (STDB) on this carefully initialized network to obtain an SNN that converges within few epochs and requires fewer time steps for input processing.
Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activations
Our results suggest that SNNs trained with LIF neurons and smaller number of timesteps are more robust than the ones with IF (Integrate-Fire) neurons and larger number of timesteps.
STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognition
We present a sparse SNN topology where non-critical connections are pruned to reduce the network size and the remaining critical synapses are weight quantized to accommodate for limited conductance levels.
