Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks

May 21, 2018 ยท Entered Twilight ยท ๐Ÿ› Neural Information Processing Systems

๐ŸŒ… TWILIGHT: Old Age
Predates the code-sharing era โ€” a pioneer of its time

"Last commit was 7.0 years ago (โ‰ฅ5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, CMakeLists.txt, Config, README.md, Result, cifar-10, common, dataAugmentation, layers, main.cpp, mnist, net.cu, net.cuh, net_spiking.cu, net_spiking.cuh, nmnist, readData, test

Authors Yingyezhe Jin, Wenrui Zhang, Peng Li arXiv ID 1805.07866 Category cs.NE: Neural & Evolutionary Cross-listed cs.LG Citations 185 Venue Neural Information Processing Systems Repository https://github.com/jinyyy666/mm-bp-snn โญ 32 Last Checked 1 month ago
Abstract
Spiking neural networks (SNNs) are positioned to enable spatio-temporal information processing and ultra-low power event-driven neuromorphic hardware. However, SNNs are yet to reach the same performances of conventional deep artificial neural networks (ANNs), a long-standing challenge due to complex dynamics and non-differentiable spike events encountered in training. The existing SNN error backpropagation (BP) methods are limited in terms of scalability, lack of proper handling of spiking discontinuities, and/or mismatch between the rate-coded loss function and computed gradient. We present a hybrid macro/micro level backpropagation (HM2-BP) algorithm for training multi-layer SNNs. The temporal effects are precisely captured by the proposed spike-train level post-synaptic potential (S-PSP) at the microscopic level. The rate-coded errors are defined at the macroscopic level, computed and back-propagated across both macroscopic and microscopic levels. Different from existing BP methods, HM2-BP directly computes the gradient of the rate-coded loss function w.r.t tunable parameters. We evaluate the proposed HM2-BP algorithm by training deep fully connected and convolutional SNNs based on the static MNIST [14] and dynamic neuromorphic N-MNIST [26]. HM2-BP achieves an accuracy level of 99.49% and 98.88% for MNIST and N-MNIST, respectively, outperforming the best reported performances obtained from the existing SNN BP algorithms. Furthermore, the HM2-BP produces the highest accuracies based on SNNs for the EMNIST [3] dataset, and leads to high recognition accuracy for the 16-speaker spoken English letters of TI46 Corpus [16], a challenging patio-temporal speech recognition benchmark for which no prior success based on SNNs was reported. It also achieves competitive performances surpassing those of conventional deep learning models when dealing with asynchronous spiking streams.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Neural & Evolutionary

R.I.P. ๐Ÿ‘ป Ghosted

LSTM: A Search Space Odyssey

Klaus Greff, Rupesh Kumar Srivastava, ... (+3 more)

cs.NE ๐Ÿ› IEEE TNNLS ๐Ÿ“š 6.0K cites 11 years ago