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

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.

arXiv comment10 pages, Submitted Manuscript

References in corpus (18)

• YOLOv3: An Incremental Improvement
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• How transferable are features in deep neural networks?
• Deep Learning in Spiking Neural Networks
• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
• STDP-based spiking deep convolutional neural networks for object recognition
• What makes for effective detection proposals?
• Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures
• Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networks
• Bio-Inspired Spiking Convolutional Neural Network using Layer-wise Sparse Coding and STDP Learning
• The Heavy-Tail Phenomenon in SGD
• Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? -- A Neural Tangent Kernel Perspective
• A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks
• A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks
• Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks
• Once more on comparison of tail index estimators
• What leads to generalization of object proposals?