Abstract
In recent years, spiking neural networks (SNNs) have attracted increasingly more researchers to study by virtue of its bio-interpretability and low-power computing. The SNN simulator is an essential tool to accomplish image classification, recognition, speech recognition, and other tasks using SNN. However, most of the existing simulators for spike neural networks are clock-driven, which has two main problems. First, the calculation result is affected by time slice, which obviously shows that when the calculation accuracy is low, the calculation speed is fast, but when the calculation accuracy is high, the calculation speed is unacceptable. The other is the failure of lateral inhibition, which severely affects SNN learning. In order to solve these problems, an event-driven high accurate simulator named EDHA (Event-Driven High Accuracy) for spike neural networks is proposed in this paper. EDHA takes full advantage of the event-driven characteristics of SNN and only calculates when a spike is generated, which is independent of the time slice. Compared with previous SNN simulators, EDHA is completely event-driven, which reduces a large amount of calculations and achieves higher computational accuracy. The calculation speed of EDHA in the MNIST classification task is more than 10 times faster than that of mainstream clock-driven simulators. By optimizing the spike encoding method, the former can even achieve more than 100 times faster than the latter. Due to the cross-platform characteristics of Java, EDHA can run on x86, amd64, ARM, and other platforms that support Java.
Highlights
In recent years, spiking neural networks (SNNs) [1] have attracted increasingly more researchers to study the related algorithms of SNNs by virtue of its bio-interpretability [1,2,3,4]and low-power computing [5,6,7,8,9,10], which is called “the third generation artificial neural network”
Spikes are used to transmit information between neurons, and the time dimension is introduced in SNN which is different from ANN
Spiking neural networks can achieve efficient spatio-temporal feature extraction relying on unsupervised learning [12], while unsupervised learning does not require sample labeling, and can save a large amount of human resources consumed by sample labeling
Summary
In recent years, spiking neural networks (SNNs) [1] have attracted increasingly more researchers to study the related algorithms of SNNs by virtue of its bio-interpretability [1,2,3,4]and low-power computing [5,6,7,8,9,10], which is called “the third generation artificial neural network”. Thanks to the event-driven computing characteristics of SNN, those neurons that are not activated will not participate in the actual computation [13], saving computing resources, which is very suitable for low-power computing on dedicated chips, for example, Truenorth [5], Tianjic [7], Loihi [6], Darwin [8], etc. Using these chips, the computational power consumption of SNN is more than 100 times lower than that of ANN [14]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
