A supervised multi-spike learning algorithm based on gradient descent for spiking neural networks

Xu, Yan; Zeng, Xiaoqin; Han, Lixin; Yang, Jing

doi:10.1016/j.neunet.2013.02.003

Cited by 145 publications

(112 citation statements)

References 27 publications

Supporting

Mentioning

112

Contrasting

Order By: Relevance

“…In Figure 12, the vertical axis shows the average Figure 11. Proposed spike shape used for processing and learning purposed [17]. Figure 12.…”

Section: Snn Instancesmentioning

confidence: 99%

Memristor Neural Network Design

Huang¹,

Zhang²,

Li³

et al. 2018

Memristor and Memristive Neural Networks

View full text Add to dashboard Cite

Neural network, a powerful learning model, has archived amazing results. However, the current Von Neumann computing system-based implementations of neural networks are suffering from memory wall and communication bottleneck problems ascribing to the Complementary Metal Oxide Semiconductor (CMOS) technology scaling down and communication gap. Memristor, a two terminal nanosolid state nonvolatile resistive switching, can provide energy-efficient neuromorphic computing with its synaptic behavior. Crossbar architecture can be used to perform neural computations because of its high density and parallel computation. Thus, neural networks based on memristor crossbar will perform better in real world applications. In this chapter, the design of different neural network architectures based on memristor is introduced, including spiking neural networks, multilayer neural networks, convolution neural networks, and recurrent neural networks. And the brief introduction, the architecture, the computing circuits, and the training algorithm of each kind of neural networks are presented by instances. The potential applications and the prospects of memristor-based neural network system are discussed.

show abstract

“…In Figure 12, the vertical axis shows the average Figure 11. Proposed spike shape used for processing and learning purposed [17]. Figure 12.…”

Section: Snn Instancesmentioning

confidence: 99%

Memristor Neural Network Design

Huang¹,

Zhang²,

Li³

et al. 2018

Memristor and Memristive Neural Networks

View full text Add to dashboard Cite

show abstract

“…In this section, first the performance of SLSNC is compared with that of other learning algorithms for spiking neural networks, namely, SpikeProp [7], MuSpiNN [13], multi-spike learning [14] and SWAT [37]. The comparison has been made for the problems of Fisher Iris plant classification and Wisconsin breast cancer.…”

Section: Performance Evaluation Of Slsncmentioning

confidence: 99%

“…Several extensions to SpikeProp have been proposed which improve its convergence characteristics by adding a momentum term [9,10] and by using adaptive learning rates [11]. Other variations of SpikeProp have also been proposed which are capable of learning with multiple spikes [12][13][14].…”

Section: Introductionmentioning

confidence: 99%

“…First, the performance of the SLSNC is compared with that of SpikeProp [7], MuSpiNN [13], Multi-spike learning [14] and Synaptic Weight Association Training (SWAT) [37] using both the Iris flower classification and Wisconsin breast cancer data sets from the UCI machine learning repository [38]. The experiments are conducted in the same setting as given in [14]. From the results, we can clearly see that the proposed SLSNC requires fewer parameters to achieve a better classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A sequential learning algorithm for a spiking neural classifier

Dora

Sundaram

Sundararajan

2015

Applied Soft Computing

View full text Add to dashboard Cite

“…Xu and el. [7] proposed a gradient descent based algorithm which can realize the multi-spike learning.…”

Section: Introductionmentioning

confidence: 99%

Two Methods to Improve the Efficacy of ReSuMe

Yang¹

2018

dtcse

Self Cite

View full text Add to dashboard Cite

Abstract. Neuron learning is the basis of the more complex learning of neuron network. Resume is the one of the most popular used supervised learning algorithm for spiking neurons. It corresponds to the Widrow-Hoff rule and its weights adjustment is derived from the spike-based Hebbian processes. Although it makes quite success the learning accuracy decreases quickly when the desired output spike train gets longer. This paper analyzes two important factors related to the learning convergence of Resume. And we proposed two methods based on them to improve the efficacy of Resume. The experimental results show that the two improved algorithms both can achieve better performance.

show abstract

A supervised multi-spike learning algorithm based on gradient descent for spiking neural networks

Cited by 145 publications

References 27 publications

Memristor Neural Network Design

Memristor Neural Network Design

A sequential learning algorithm for a spiking neural classifier

Two Methods to Improve the Efficacy of ReSuMe

Contact Info

Product

Resources

About