2
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Enabling Spike-based Backpropagation in State-of-the-art Deep Neural Network Architectures

      Preprint
      , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Spiking Neural Networks (SNNs) has recently emerged as a prominent neural computing paradigm. However, the typical shallow spiking network architectures have limited capacity for expressing complex representations, while training a very deep spiking network have not been successful so far. Diverse methods have been proposed to get around this issue such as converting off-line trained deep Artificial Neural Networks (ANNs) to SNNs. However, ANN-to-SNN conversion scheme fails to capture the temporal dynamics of a spiking system. On the other hand, it is still a difficult problem to directly train deep SNNs using input spike events due to the discontinuous and non-differentiable nature of the spike signals. To overcome this problem, we propose using differentiable (but approximate) activation for Leaky Integrate-and-Fire (LIF) spiking neurons to train deep convolutional SNNs with input spike events using spike-based backpropagation algorithm. Our experiments show the effectiveness of the proposed spike-based learning strategy on state-of-the-art deep networks (VGG and Residual architectures) by achieving the best classification accuracies in MNIST, SVHN and CIFAR-10 datasets compared to other SNNs trained with spike-based learning. Moreover, we analyze sparse event-driven computations to demonstrate the efficacy of proposed SNN training method for inference operation in the spiking domain.

          Related collections

          Most cited references11

          • Record: found
          • Abstract: not found
          • Article: not found

          Error-backpropagation in temporally encoded networks of spiking neurons

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Overview of the SpiNNaker System Architecture

              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Spiking Deep Convolutional Neural Networks for Energy-Efficient Object Recognition

                Bookmark

                Author and article information

                Journal
                15 March 2019
                Article
                1903.06379
                96f2ec3d-619c-4975-a735-dd7cd683d157

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                History
                Custom metadata
                Chankyu Lee and Syed Shakib Sarwar contributed equally to the work
                cs.NE

                Neural & Evolutionary computing
                Neural & Evolutionary computing

                Comments

                Comment on this article