Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification

Neural networks (SNNs) can potentially offer an efficient way of doing inference because the neurons in the networks are sparsely activated and computations are event-driven. Previous work showed that simple continuous-valued deep Convolutional Neural Networks (CNNs) can be converted into accurate spiking equivalents. These networks did not include certain common operations such as max-pooling, softmax, batch-normalization and Inception-modules. This paper presents spiking equivalents of these operations therefore allowing conversion of nearly arbitrary CNN architectures. We show conversion of popular CNN architectures, including VGG-16 and Inception-v3, into SNNs that produce the best results reported to date…

• SA
  Samsung Advanced Institute of Technology
• ET
  Eidgenössische Technische Hochschule Zürich
• UZ
  Universität Zürich
• S
  Samsung