scholarly journals EDHA: Event-Driven High Accurate Simulator for Spike Neural Networks

Electronics ◽  
2021 ◽  
Vol 10 (18) ◽  
pp. 2281
Author(s):  
Lingfei Mo ◽  
Xinao Chen ◽  
Gang Wang
Keyword(s):  
Neural Networks ◽  
High Accuracy ◽  
The Other ◽  
Spiking Neural Networks ◽  
Time Slice ◽  
Computational Accuracy ◽  
Low Power Computing ◽  
Event Driven ◽  
Cross Platform ◽  
Encoding Method

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.

scholarly journals Biological modelling of a computational spiking neural network with neuronal avalanches

2017 ◽  
Vol 375 (2096) ◽  
pp. 20160286 ◽  
Author(s):  
Xiumin Li ◽  
Qing Chen ◽  
Fangzheng Xue
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Critical State ◽  
Spike Timing ◽  
Spiking Neural Networks ◽  
Mathematical Methods ◽  
Computational Accuracy ◽  
Active Neuron ◽  
Computational Performance ◽  
Neuronal Avalanches

In recent years, an increasing number of studies have demonstrated that networks in the brain can self-organize into a critical state where dynamics exhibit a mixture of ordered and disordered patterns. This critical branching phenomenon is termed neuronal avalanches. It has been hypothesized that the homeostatic level balanced between stability and plasticity of this critical state may be the optimal state for performing diverse neural computational tasks. However, the critical region for high performance is narrow and sensitive for spiking neural networks (SNNs). In this paper, we investigated the role of the critical state in neural computations based on liquid-state machines, a biologically plausible computational neural network model for real-time computing. The computational performance of an SNN when operating at the critical state and, in particular, with spike-timing-dependent plasticity for updating synaptic weights is investigated. The network is found to show the best computational performance when it is subjected to critical dynamic states. Moreover, the active-neuron-dominant structure refined from synaptic learning can remarkably enhance the robustness of the critical state and further improve computational accuracy. These results may have important implications in the modelling of spiking neural networks with optimal computational performance. This article is part of the themed issue ‘Mathematical methods in medicine: neuroscience, cardiology and pathology’.

scholarly journals Event-Driven Simulations of Nonlinear Integrate-and-Fire Neurons

2007 ◽  
Vol 19 (12) ◽  
pp. 3226-3238 ◽  
Author(s):  
Arnaud Tonnelier ◽  
Hana Belmabrouk ◽  
Dominique Martinez
Keyword(s):  
Neural Networks ◽  
Spiking Neural Networks ◽  
Synaptic Currents ◽  
Fire Model ◽  
Integrate And Fire ◽  
Fire Models ◽  
Event Driven

Event-driven strategies have been used to simulate spiking neural networks exactly. Previous work is limited to linear integrate-and-fire neurons. In this note, we extend event-driven schemes to a class of nonlinear integrate-and-fire models. Results are presented for the quadratic integrate-and-fire model with instantaneous or exponential synaptic currents. Extensions to conductance-based currents and exponential integrate-and-fire neurons are discussed.

A novel time-event-driven algorithm for simulating spiking neural networks based on circular array

2018 ◽  
Vol 292 ◽  
pp. 121-129 ◽  
Author(s):  
Xia Peng ◽  
Zhijie Wang ◽  
Fang Han ◽  
Guangxiao Song ◽  
Shenyi Ding
Keyword(s):  
Neural Networks ◽  
Spiking Neural Networks ◽  
Circular Array ◽  
Event Driven

scholarly journals An Event-Driven Classifier for Spiking Neural Networks Fed with Synthetic or Dynamic Vision Sensor Data

2017 ◽  
Vol 11 ◽  
Author(s):  
Evangelos Stromatias ◽  
Miguel Soto ◽  
Teresa Serrano-Gotarredona ◽  
Bernabé Linares-Barranco
Keyword(s):  
Neural Networks ◽  
Spiking Neural Networks ◽  
Sensor Data ◽  
Vision Sensor ◽  
Dynamic Vision ◽  
Event Driven

A Distributed Peer to Peer Simulator

2013 ◽  
Vol 457-458 ◽  
pp. 830-833
Author(s):  
Li Yan ◽  
Rui Shen
Keyword(s):  
Large Scale ◽  
High Accuracy ◽  
Peer To Peer ◽  
Resource Consumption ◽  
Large Scale Simulation ◽  
Event Driven ◽  
Cross Platform ◽  
Simulator Test

This paper proposed a new distributed peer to peer simulator. The simulator uses message-based event-driven engine with large-scale simulation supported and Cross-platform. Simulator supports multiple protocols, using this simulator test peer to peer agreement, not only to ensure high accuracy, but also effectively reduce the resource consumption and improve the efficiency of the simulation.

Sign in / Sign up

Export Citation Format

Share Document