A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detection

TL;DR

This paper introduces a Fully Spiking Hybrid Neural Network that achieves high energy efficiency and robustness for object detection, combining unsupervised and supervised learning methods, and outperforming traditional DNNs in noisy and low-data scenarios.

Contribution

The paper presents a novel hybrid neural network architecture that integrates spike-based learning with back-propagation, enhancing energy efficiency and robustness in object detection tasks.

Findings

150X energy efficiency over DNNs

Better accuracy on noisy data

Lower uncertainty error with less labeled data

Abstract

This paper proposes a Fully Spiking Hybrid Neural Network (FSHNN) for energy-efficient and robust object detection in resource-constrained platforms. The network architecture is based on Convolutional SNN using leaky-integrate-fire neuron models. The model combines unsupervised Spike Time-Dependent Plasticity (STDP) learning with back-propagation (STBP) learning methods and also uses Monte Carlo Dropout to get an estimate of the uncertainty error. FSHNN provides better accuracy compared to DNN based object detectors while being 150X energy-efficient. It also outperforms these object detectors, when subjected to noisy input data and less labeled training data with a lower uncertainty error.