A Novel Conversion Method for Spiking Neural Network using Median Quantization

Zou, Chenglong; Cui, Xiaoxin; Ge, Jiexian; Ma, Hanghang; Wang, Xinan

doi:10.1109/iscas45731.2020.9180918

Cited by 6 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it still brings a great drop in accuracy on some large-scale datasets like CIFAR-10, and usually needs many (hundreds or thousands, even more on ImageNet [48] ) time steps to achieve satisfactory performances. On the other way, the works [28,30,31,[33][34][35]37,40] choose to optimize firing threshold while keeping the weight parameters of networks unchanged, to strive for the same correlation effect. An appropriate threshold can be obtained by similar activation normalization methods [27,29] or directly computed from the related network variables of target ANN counterparts.…”

Section: Existing Conversion Methods For Snnsmentioning

confidence: 99%

“…An appropriate threshold can be obtained by similar activation normalization methods [27,29] or directly computed from the related network variables of target ANN counterparts. [30,35,37,40] However, this layer-bylayer threshold scaling is more coarse grained and couldn't be well compatible with widely used elements like BN [41] or deeper architectures. [1,39,49] Based on previous works, [28,34] different quantization methods are adopted to optimize both of the weights and thresholds and achieve more faster and highaccuracy performances.…”

Section: Existing Conversion Methods For Snnsmentioning

confidence: 99%

“…Compared with the original median quantization algorithm, [40] we modified it by removing upper bound restrictions, which allowed us to quantize wider range of values and helped obtain a more accurate reference ANN than theirs. This improvement will be discussed in the next section.…”

Section: Training With Quantizationmentioning

confidence: 99%

See 2 more Smart Citations

Toward a Lossless Conversion for Spiking Neural Networks with Negative‐Spike Dynamics

Zou,

Cui,

Chen

et al. 2023

Advanced Intelligent Systems

Self Cite

View full text Add to dashboard Cite

Spiking neural networks (SNNs) become popular choices for processing spatiotemporal input data and enabling low‐power event‐driven spike computation on neuromorphic processors. However, direct SNN training algorithms are not well compatible with error back‐propagation process, while indirect conversion algorithms based on artificial neural networks (ANNs) are usually accuracy–lossy due to various approximation errors. Both of them suffer from lower accuracies compared with their reference ANNs and need lots of time steps to achieve stable performance in deep architectures. In this article, a novel conversion framework is presented for deep SNNs with negative‐spike dynamics, which takes a quantization constraint and spike compensation technique into consideration during ANN‐to‐SNN conversion, and a truly lossless accuracy performance with their ANN counterparts is obtained. The converted SNNs can retain full advantages of simple leaky‐integrate‐and‐fire spiking neurons and are very suited for hardware implementation. In the experimental results, it is shown that converted spiking LeNet on MNIST/FashionMNIST and VGG‐Net on CIFAR‐10 dataset yield the state‐of‐the‐art classification accuracies with quite shortened computing time steps and much fewer synaptic operations.

show abstract

Section: Existing Conversion Methods For Snnsmentioning

confidence: 99%

Section: Existing Conversion Methods For Snnsmentioning

confidence: 99%

See 1 more Smart Citation

Toward a Lossless Conversion for Spiking Neural Networks with Negative‐Spike Dynamics

Zou,

Cui,

Chen

et al. 2023

Advanced Intelligent Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…To ensure that the accuracy of the converted SNN is close to that of the ANN, two approaches are commonly used: 1) Adjusting the ANN properties before training to account for SNN limitations and 2) reducing approximation errors of the SNN during conversion. Examples for the first approach include removing the bias, changing the activation to ReLU [10], clipping ANN activations to the range [0, 1] [11], and adopting quantized ReLU in ANNs [12], [13]. Falling into the second category, different weight normalization methods have been proposed to reduce approximation errors caused by the limited dynamic range of SNN neurons.…”

Section: Introductionmentioning

confidence: 99%

Reducing Latency in a Converted Spiking Video Segmentation Network

Cheni

Rueckauer

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

Spiking Neural Networks (SNNs) can be configured to produce almost-equivalent accurate Analog Neural Networks (ANNs) by various ANN-SNN conversion methods. Most of these methods are applied to classification and object detection networks tested on frame-based datasets. In this work, we demonstrate a converted SNN for image segmentation and applied to a natural video dataset. Instead of resetting the network state with each input frame, we capitalize on the temporal redundancy between adjacent frames in a natural scene, and propose an interval reset method where the network state is reset after a fixed number of frames. We studied the trade-off between accuracy and latency with the number of interval reset frames. We also applied layer-specific normalization and early stopping to speed up network convergence and to reduce the latency. Our results show that the SNN achieved a 35.7x increase in convergence speed with only 1.5% accuracy drop using an interval reset of 20 frames.

show abstract

“…For this purpose, we first introduce an adjustable quantized algorithm in ANN training to minimize the spike approximation errors, which are commonly existed in ANN-to-SNN conversion and propose a scatter-and-gather conversion mechanism for SNNs. This work is based on our previous algorithm (Zou et al, 2020 ) and hardware (Kuang et al, 2021 ), and we extend it by (a) testing its robustness on input noise and larger dataset (CIFAR-100), (b) developing a incremental mapping framework to carry out an efficient network deployment on a typical crossbar-based neuromorphic chip, (c) detailed power and speed analyses are given to show its excellent application potential. All together, the main contributions of this article are summarized as follows:…”

Section: Introductionmentioning

confidence: 99%

A Scatter-and-Gather Spiking Convolutional Neural Network on a Reconfigurable Neuromorphic Hardware

et al. 2021

Self Cite

View full text Add to dashboard Cite

Artificial neural networks (ANNs), like convolutional neural networks (CNNs), have achieved the state-of-the-art results for many machine learning tasks. However, inference with large-scale full-precision CNNs must cause substantial energy consumption and memory occupation, which seriously hinders their deployment on mobile and embedded systems. Highly inspired from biological brain, spiking neural networks (SNNs) are emerging as new solutions because of natural superiority in brain-like learning and great energy efficiency with event-driven communication and computation. Nevertheless, training a deep SNN remains a main challenge and there is usually a big accuracy gap between ANNs and SNNs. In this paper, we introduce a hardware-friendly conversion algorithm called “scatter-and-gather” to convert quantized ANNs to lossless SNNs, where neurons are connected with ternary {−1,0,1} synaptic weights. Each spiking neuron is stateless and more like original McCulloch and Pitts model, because it fires at most one spike and need be reset at each time step. Furthermore, we develop an incremental mapping framework to demonstrate efficient network deployments on a reconfigurable neuromorphic chip. Experimental results show our spiking LeNet on MNIST and VGG-Net on CIFAR-10 datasetobtain 99.37% and 91.91% classification accuracy, respectively. Besides, the presented mapping algorithm manages network deployment on our neuromorphic chip with maximum resource efficiency and excellent flexibility. Our four-spike LeNet and VGG-Net on chip can achieve respective real-time inference speed of 0.38 ms/image, 3.24 ms/image, and an average power consumption of 0.28 mJ/image and 2.3 mJ/image at 0.9 V, 252 MHz, which is nearly two orders of magnitude more efficient than traditional GPUs.

show abstract

A Novel Conversion Method for Spiking Neural Network using Median Quantization

Cited by 6 publications

References 12 publications

Toward a Lossless Conversion for Spiking Neural Networks with Negative‐Spike Dynamics

Toward a Lossless Conversion for Spiking Neural Networks with Negative‐Spike Dynamics

Reducing Latency in a Converted Spiking Video Segmentation Network

A Scatter-and-Gather Spiking Convolutional Neural Network on a Reconfigurable Neuromorphic Hardware

Contact Info

Product

Resources

About