Solving a classification task by spiking neurons with STDP and temporal coding

Sboev, Alexander; Vlasov, Danila; Rybka, Roman; Serenko, Alexey

doi:10.1016/j.procs.2018.01.075

Cited by 15 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GRF Encoding: The GRF encoding method was adopted on the original data, which has been used for performing image classification for input-data-transformation. [42] For this method, each of the features of an input vector was encoded by a population of N neurons, where the individual neurons received either a spike or no spike. Each of the features of the input vector, in this case, the HRS, LRS, V set , and V reset was filled with N Gaussian peaks with selected standard deviation and mean values using Equations (5)(6).…”

Section: Methodsmentioning

confidence: 99%

Continual Learning Electrical Conduction in Resistive‐Switching‐Memory Materials

Wang

et al. 2022

Advcd Theory and Sims

View full text Add to dashboard Cite

The authors apply the concept of continual learning to modeling conductive‐filament growth in resistive‐switching materials (RSM). The approach permits computation of compliance current without knowing the geometries of conductive filaments and switching behaviors. This avoids the need to retrain the entire dataset when additional compliance currents are considered and is thus ideal for resistive switching (RS) thin films, doped layers, and other material systems. Computation of compliance current is consistent with experimental data for a wide range of parameters and learning tasks and demonstrates switching behavior not captured by traditional models. Lesion calculations elucidate the brain‐inspired‐modification‐facilitated increase in compliance‐current‐computation‐accuracy. A state‐of‐the‐art performance on challenging compliance‐current learning tasks without storing data is achieved (“brain inspired replay (BIR) – gating based on internal context (Gat)” method, ≈89%; above a benchmark of ≈50% for synaptic‐intelligence (SI)/elastic‐weight‐consolidation (EWC) methods), and it provides a novel model for computing compliance current based on replay of the brain. This intuitive approach combined with a simple solver tool, allows researchers with little computation experience to perform realistic and accurate modeling.

show abstract

Section: Methodsmentioning

confidence: 99%

Continual Learning Electrical Conduction in Resistive‐Switching‐Memory Materials

Wang

et al. 2022

Advcd Theory and Sims

View full text Add to dashboard Cite

show abstract

“…The classification accuracy of the proposed learning model is compared to some existing SNN learning models for data classification. The existing models that we compared our model to include; SpikeProp [15], Multi-Spike(GMES) [16], STDPM [40], MultiSp [14], MuSpiNN [34], SRESN [18]. Similar to the proposed model, all the existing models encode the continuous values in the datasets to spike times using population coding.…”

Section: B Comparison With Existing Learning Methodsmentioning

confidence: 99%

“…The Gaussian Receptive Fields (GRF) based population temporal coding scheme proposed by [15] and used by [14], [34], [40], is used in this paper. Each attribute, a, with a range, {a n min , .…”

Section: ) Network Setup and Learning Parametersmentioning

confidence: 99%

A Multi-Spiking Neural Network Learning Model for Data Classification

et al. 2020

View full text Add to dashboard Cite

Classical Artificial Neural Networks (ANNs) though well exploited in solving classification problems, do not model perfectly the information encoding process in the human brain because ANNs encode information using rate-based coding. However, biological neurons in the brain are known to encode information using temporal coding. In order to mimic the biological method of encoding information, various Spiking Neural Network (SNN) models have been developed. However, some of these models are limited in the number of spikes and do not leverage well on some classification problems. In order to address some of the inherent challenges associated with SNN, a multi-layer learning model for a multi-spiking network is proposed in this paper. The model exploits the temporal coding of spikes and the least-squares method to derive a weight update scheme. It also employs a spike locality concept in order to determine how the synaptic weights are to be adjusted at a particular spike time so as to minimize the learning interference, and thereby, increasing the number of spikes for learning. The performance of the model is evaluated on benchmarked classification datasets. A correlation-based metric is combined with a threshold concept to measure the classification accuracy of the model. The experimental results showed that the proposed model achieved better classification accuracy than some state-of-the-art multi-layer SNN learning models. INDEX TERMS Multi-spiking neural network, supervised learning, temporal coding.

show abstract

“…However, like in most of ANNs learning algorithms, SNNs learning methods employ synaptic weights as the principal learning parameter. Various supervised [6], [28], and unsupervised Spike-Timing-Dependent Plasticity (STDP) [29], [30] learning algorithms had been proposed which employed SNNs synaptic weights as the principal learning parameters. Delays of the synapses had been used as extra and supporting variables for the learning task [6], [31]- [34].…”

Section: Related Workmentioning

confidence: 99%

Automated Adaptive Threshold-Based Feature Extraction and Learning for Spiking Neural Networks

Amin

2021

IEEE Access

View full text Add to dashboard Cite

Over the past years Spiking Neural Networks (SNNs) models became attractive as a possible bridge to enable low-power event-driven neuromorphic hardware. SNNs have a high computational power due to the implicit employment of the biologically inspired input times. SNNs employ various parameters such as neuron threshold, synaptic delays, and weights in their structures. However, SNNs applications are still limited and elementary compared with other neural network architectures such as the Convolution Neural Networks (CNNs). In this research, a new SNN-based model named Adaptive Threshold Module (ATM) and its algorithm are proposed. The proposed ATM and algorithm depend on the adaptation of the internal spiking neuron threshold level. Adapting the threshold of the neurons is employed to control the spiking neuron firing rate to uniquely extract the main features of the input pattern that is in the shape of spike trains. It is shown that this technique works as an automated feature extraction method of input patterns in an efficient and faster way than other methods. The proposed method can preserve all information of the input spike trains. Simulations of the proposed model and the algorithm, using the challenging speech TIDIGITS dataset, sound RWCP dataset, and Poisson distribution spike trains, show encouraging results. The ATM can make SNN provide an accuracy surpassing that of the current state-of-the-art SNN algorithms and conventional non-spiking learning models.

show abstract

Solving a classification task by spiking neurons with STDP and temporal coding

Cited by 15 publications

References 12 publications

Continual Learning Electrical Conduction in Resistive‐Switching‐Memory Materials

Continual Learning Electrical Conduction in Resistive‐Switching‐Memory Materials

A Multi-Spiking Neural Network Learning Model for Data Classification

Automated Adaptive Threshold-Based Feature Extraction and Learning for Spiking Neural Networks

Contact Info

Product

Resources

About