Time Step Impact on Performance and Accuracy of Izhikevich Neuron: Software Simulation and Hardware Implementation

Heidarpur, Moslem; Ahmadi, Arash; Ahmadi, M.

doi:10.1109/iscas45731.2020.9180632

Cited by 6 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Actually, the parameter time step dt has a significant effect on performance and cost of implementation 35 . As it is demonstrated in Figure 15, some of responses are showed with dt = 0.25 and others with dt = 1.…”

Section: Resultsmentioning

confidence: 98%

Implementation of Izhikevich neuron based on stochastic computing using a novel inspired Omega‐Flip stochastic number generator

Hedayatpour

Karami

Shamsi

2022

Circuit Theory & Apps

View full text Add to dashboard Cite

This paper presents an optimized stochastic multiplier to implement Izhikevich spiking neuron model. A novel stochastic number generator is used as the main block for stochastic computing to design a stochastic multiplier. The designed multiplier was used to describe and implement Izhikevich neuron model equation which is capable to produce variant responses of spiking neurons. To the best of the author's knowledge, this work is the pioneer using a designed multiplier for computing all of the multiplication expressions in spiking neuron equation. The effect of increasing number of bit streams on the accuracy of stochastic computing is studied. Furthermore, some numerical intervals that are more prone to the error are found and illustrated upon stochastic computing usage, and a method is proposed to improve the error prone numerical intervals. In addition, the response accuracy is optimized by changing time step parameter in solving ordinary differential Izhikevich neuron model equation using Euler's method. Hence, a 13‐bit stochastic multiplier is designed. It is found that variations in parameters a and b have a profound effect on the accuracy of recovery variable u and, consequently, on the responses. Out of 20 responses of Izhikevich neuron model, 11 responses are generated using the proposed stochastic computing method and compared with piecewise linear method and some previous architectures of Izhikevich neuron model implementations.

show abstract

Section: Resultsmentioning

confidence: 98%

Implementation of Izhikevich neuron based on stochastic computing using a novel inspired Omega‐Flip stochastic number generator

Hedayatpour

Karami

Shamsi

2022

Circuit Theory & Apps

View full text Add to dashboard Cite

show abstract

“…However, this poses a big challenge in robotics and biomedical engineering because the amount of real-time operations that can be performed is limited by the utilization of embedded systems. To allocate optimally the resources of microprocessors, we seek a trade-off between number of operations performed and accuracy, by investigating the best Ordinary Differential Equation (ODE) solver and discretization time τ (Heidarpur et al [2020]). In fact, the model is sensitive to the τ used (Heidarpur et al [2020]), and the bigger it gets, the more the spike timing accumulates a delay with respect to the ideal solution.…”

Section: Introduction 1motivationmentioning

confidence: 99%

“…To allocate optimally the resources of microprocessors, we seek a trade-off between number of operations performed and accuracy, by investigating the best Ordinary Differential Equation (ODE) solver and discretization time τ (Heidarpur et al [2020]). In fact, the model is sensitive to the τ used (Heidarpur et al [2020]), and the bigger it gets, the more the spike timing accumulates a delay with respect to the ideal solution. This effect is evident in the three ODE solvers we are going to show in the paper.…”

Section: Introduction 1motivationmentioning

confidence: 99%

Euler method can outperform more complex ODE solvers in the numerical implementation of the Izhikevich artificial Spiking Neuron Model given the allocated FLOPS

Alteriis

Cataldo

Mazzoni³

et al. 2021

Preprint

View full text Add to dashboard Cite

The Izhikevich artificial spiking neuron model is among the most employed models in neuromorphic engineering and computational neuroscience, due to the affordable computational effort to discretize it and its biological plausibility. It has been adopted also for applications with limited computational resources in embedded systems. It is important therefore to realize a compromise between error and computational expense to solve numerically the model’s equations. Here we investigate the effects of discretization and we study the solver that realizes the best compromise between accuracy and computational cost, given an available amount of Floating Point Operations per Second (FLOPS). We considered three fixed-step solvers for Ordinary Differential Equations (ODE), commonly used in computational neuroscience: Euler method, the Runge-Kutta 2 method and the Runge-Kutta 4 method. To quantify the error produced by the solvers, we used the Victor Purpura spike train Distance from an ideal solution of the ODE. Counterintuitively, we found that simple methods such as Euler and Runge Kutta 2 can outperform more complex ones (i.e. Runge Kutta 4) in the numerical solution of the Izhikevich model if the same FLOPS are allocated in the comparison. Moreover, we quantified the neuron rest time (with input under threshold resulting in no output spikes) necessary for the numerical solution to converge to the ideal solution and therefore to cancel the error accumulated during the spike train; in this analysis we found that the required rest time is independent from the firing rate and the spike train duration. Our results can generalize in a straightforward manner to other spiking neuron models and provide a systematic analysis of fixed step neural ODE solvers towards an accuracy-computational cost tradeoff.

show abstract

The input-dependent variable sampling (I-DEVS) energy-efficient digital neuron implementation method

2023

View full text Add to dashboard Cite

Time Step Impact on Performance and Accuracy of Izhikevich Neuron: Software Simulation and Hardware Implementation

Cited by 6 publications

References 27 publications

Implementation of Izhikevich neuron based on stochastic computing using a novel inspired Omega‐Flip stochastic number generator

Implementation of Izhikevich neuron based on stochastic computing using a novel inspired Omega‐Flip stochastic number generator

Euler method can outperform more complex ODE solvers in the numerical implementation of the Izhikevich artificial Spiking Neuron Model given the allocated FLOPS

The input-dependent variable sampling (I-DEVS) energy-efficient digital neuron implementation method

Contact Info

Product

Resources

About