On the accuracy and computational cost of spiking neuron implementation

Valadez-Godínez, Sergio; Sossa, Humberto; Santiago-Montero, Raúl

doi:10.1016/j.neunet.2019.09.026

Cited by 19 publications

(31 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Depending on the numerical method and SN, the accuracy increases monotonically as the step size reduces [61,81,34,72,29]. This is consistent with the theory of numerical methods where the solution provided by a convergent method approximates the exact solution as the step size tends to zero [26,10,24,20,25].…”

Section: Introductionsupporting

confidence: 82%

“…As opposed to other bi-dimensional models (e.g., the quartic [78] or the adaptive exponential [7]), the IZH adaptation variable blows up without a threshold value [77]. This makes the model sensitive to threshold values and, as a consequence, the step size must be small to avoid an alteration in the system dynamics [77,79].This agrees with practical works where a high-order numerical method and a small step were necessary to obtain an accurate implementation [35,72,81]. Figure 1 (middle) depicts the considerable lag generated by the IZH as the simulation window increases.…”

Section: Introductionsupporting

confidence: 75%

“…Even though there are several open issues in the single SN simulation, this paper focuses on the time span and firing rate influence. It is thought that the firing rate changes the accuracy that some studies [50,72,81] have included it, but its impact has not been measured. The influence of the time span variability has been ignored and, in consequence, remains unknown.…”

Section: Introductionmentioning

confidence: 99%

“…The influence of the time span variability has been ignored and, in consequence, remains unknown. Most current works have carried out simulations just on a single time span [31,27,68,47,71,52,6,59,66,58,79,29,72,34,81].…”

Section: Introductionmentioning

confidence: 99%

“…This study describes how the accuracy, computational cost, and efficiency of an SN simulation are influenced by the time span and firing rate variability. We followed and extended the studies carried out in [72] and [81] where three important SNs were investigated: the LIF, IZH, and HH. In those works, each SN was solved with three different numerical methods and five different time steps.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

How the Accuracy and Computational Cost of Spiking Neuron Simulation are Affected by the Time Span and Firing Rate

Godinez

Azuela

Santiago-Montero

2018

CyS

View full text Add to dashboard Cite

It is known that, depending on the numerical method, the simulation accuracy of a spiking neuron increases monotonically and that the computational cost increases in a power-law complexity as the time step reduces. Moreover, the mechanism responsible for generating the action potentials also affects the accuracy and computational cost. However, little attention has been paid to how the time span and firing rate influence the simulation. This study describes how the time span and firing rate variables affect the accuracy, computational cost, and efficiency. It was found that the simulation is importantly affected by these two variables.

show abstract

Section: Introductionsupporting

confidence: 82%

Section: Introductionsupporting

confidence: 75%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

How the Accuracy and Computational Cost of Spiking Neuron Simulation are Affected by the Time Span and Firing Rate

Godinez

Azuela

Santiago-Montero

2018

CyS

View full text Add to dashboard Cite

show abstract

Edge and anomaly detection of brain magnetic resonance images in a distributed environment

Chaoui

Ghomari

Meftah

2021

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Today, all scientific advancements related to medical image processing aim to develop a unique computational model. The latter will mimic the way humans interpret images. In the present paper, we propose a formal approach biologically inspired by the human natural vision system’s mechanisms. To that end, we use the spiking neural network model for edge detection in brain MRI images. The optimal results provided by this last step increase performance, and facilitate the process of anomaly detection. For that, we have developed a tool called Edge and Anomaly Detection of Brain MRI Images in Distributed Environment (EADBMIDE). It is tested on an MRI brain tumour dataset, which shows the effectiveness of the proposed methods. Each stage in this tool is compared separately with similar approaches in the literature. The obtained results show a significant improvement, making this a recommended tool for edge and anomaly detection methods in MRI images.

show abstract