DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networks

by   Nitin Rathi, et al.

Bio-inspired spiking neural networks (SNNs), operating with asynchronous binary signals (or spikes) distributed over time, can potentially lead to greater computational efficiency on event-driven hardware. The state-of-the-art SNNs suffer from high inference latency, resulting from inefficient input encoding, and sub-optimal settings of the neuron parameters (firing threshold, and membrane leak). We propose DIET-SNN, a low latency deep spiking network that is trained with gradient descent to optimize the membrane leak and the firing threshold along with other network parameters (weights). The membrane leak and threshold for each layer of the SNN are optimized with end-to-end backpropagation to achieve competitive accuracy at reduced latency. The analog pixel values of an image are directly applied to the input layer of DIET-SNN without the need to convert to spike-train. The information is converted into spikes in the first convolutional layer where leaky-integrate-and-fire (LIF) neurons integrate the weighted inputs and generate an output spike when the membrane potential crosses the trained firing threshold. 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. The reduced latency combined with high activation sparsity provides large improvements in computational efficiency. We evaluate DIET-SNN on image classification tasks from CIFAR and ImageNet datasets on VGG and ResNet architectures. We achieve top-1 accuracy of 66.52 latency) on the ImageNet dataset with 3.1X less compute energy than an equivalent standard ANN. Additionally, DIET-SNN performs 5-100X faster inference compared to other state-of-the-art SNN models.


page 1

page 2

page 3

page 4


DCT-SNN: Using DCT to Distribute Spatial Information over Time for Learning Low-Latency Spiking Neural Networks

Spiking Neural Networks (SNNs) offer a promising alternative to traditio...

Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation

Spiking Neural Networks (SNNs) operate with asynchronous discrete events...

RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network

Spiking Neural Networks (SNNs) have recently attracted significant resea...

Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratch

Spiking Neural Networks (SNNs) have recently emerged as an alternative t...

HW/SW Codesign for Robust and Efficient Binarized SNNs by Capacitor Minimization

Using accelerators based on analog computing is an efficient way to proc...

PokeBNN: A Binary Pursuit of Lightweight Accuracy

Top-1 ImageNet optimization promotes enormous networks that may be impra...

Spatio-Temporal Pruning and Quantization for Low-latency Spiking Neural Networks

Spiking Neural Networks (SNNs) are a promising alternative to traditiona...

Please sign up or login with your details

Forgot password? Click here to reset