Spiking Approximations of the MaxPooling Operation in Deep SNNs

by   Ramashish Gaurav, et al.

Spiking Neural Networks (SNNs) are an emerging domain of biologically inspired neural networks that have shown promise for low-power AI. A number of methods exist for building deep SNNs, with Artificial Neural Network (ANN)-to-SNN conversion being highly successful. MaxPooling layers in Convolutional Neural Networks (CNNs) are an integral component to downsample the intermediate feature maps and introduce translational invariance, but the absence of their hardware-friendly spiking equivalents limits such CNNs' conversion to deep SNNs. In this paper, we present two hardware-friendly methods to implement Max-Pooling in deep SNNs, thus facilitating easy conversion of CNNs with MaxPooling layers to SNNs. In a first, we also execute SNNs with spiking-MaxPooling layers on Intel's Loihi neuromorphic hardware (with MNIST, FMNIST, CIFAR10 dataset); thus, showing the feasibility of our approach.


page 12

page 17


Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networks

Deep convolutional neural networks (CNNs) have shown great potential for...

A New Neuromorphic Computing Approach for Epileptic Seizure Prediction

Several high specificity and sensitivity seizure prediction methods with...

Learning from Event Cameras with Sparse Spiking Convolutional Neural Networks

Convolutional neural networks (CNNs) are now the de facto solution for c...

Classifying Images with Few Spikes per Neuron

Spiking neural networks (SNNs) promise to provide AI implementations wit...

Spiking Deep Residual Network

Recently, spiking neural network (SNN) has received significant attentio...

TCL: an ANN-to-SNN Conversion with Trainable Clipping Layers

Spiking Neural Networks (SNNs) provide significantly lower power dissipa...

Neuromorphic Acceleration for Approximate Bayesian Inference on Neural Networks via Permanent Dropout

As neural networks have begun performing increasingly critical tasks for...