Going Deeper in Spiking Neural Networks: VGG and Residual Architectures

  title={Going Deeper in Spiking Neural Networks: VGG and Residual Architectures},
  author={A. Sengupta and Yuting Ye and Robert Y. Wang and C. Liu and K. Roy},
  journal={Frontiers in Neuroscience},
  • A. Sengupta, Yuting Ye, +2 authors K. Roy
  • Published 2019
  • Computer Science, Psychology, Medicine
  • Frontiers in Neuroscience
  • Over the past few years, Spiking Neural Networks (SNNs) have become popular as a possible pathway to enable low-power event-driven neuromorphic hardware. [...] Key Method Our technique applies to both VGG and Residual network architectures, with significantly better accuracy than the state-of-the-art. Finally, we present analysis of the sparse event-driven computations to demonstrate reduced hardware overhead when operating in the spiking domain.Expand Abstract
    Deep Learning in Spiking Neural Networks
    • 179
    • PDF
    Direct Training for Spiking Neural Networks: Faster, Larger, Better
    • 44
    • Highly Influenced
    • PDF
    Gradient Descent for Spiking Neural Networks
    • 104
    • PDF
    Enabling Spike-Based Backpropagation for Training Deep Neural Network Architectures
    • 27
    • PDF
    S4NN: temporal backpropagation for spiking neural networks with one spike per neuron
    • 17
    • PDF
    Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation
    • 11
    • Highly Influenced
    • PDF


    Publications referenced by this paper.
    Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing
    • 381
    • Highly Influential
    Convolutional networks for fast, energy-efficient neuromorphic computing
    • 390
    • PDF
    Going deeper with convolutions
    • 19,987
    • PDF
    Spiking Deep Convolutional Neural Networks for Energy-Efficient Object Recognition
    • 293
    • Highly Influential
    Unsupervised learning of digit recognition using spike-timing-dependent plasticity
    • 454
    • Highly Influential
    • PDF
    Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification
    • 166
    • Highly Influential
    • PDF