FPGA Implementation of an Evolving Spiking Neural Network

Zuppicich, Alan; Soltic, Snjezana

doi:10.1007/978-3-642-02490-0_137

Cited by 6 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are a large variety of general spiking neural network implementations in hardware [21], [86], [169], [323]- [570]. These implementations utilize a variety of neuron models such as the various integrate-and-fire neurons listed above or the more biologically-plausible or biologically-inspired models.…”

Section: Network Modelsmentioning

confidence: 99%

“…They can also be used to optimize within the characteristics and peculiarities of a particular hardware implementation (or even the characteristics and peculiarities of a particular hardware device instance). Off-chip naturebased implementations include differential evolution [1321]- [1324], evolutionary or genetic algorithms [484]- [487], [512], [570], [680], [700], [1076], [1082]- [1085], [1092], [1325]- [1337], and particle swarm optimization [1338]. We explicitly specify these off-chip methods because all of the nature-based implementations rely on evaluations of a current network solution and can utilize the chip during the training process (as a chip-in-the-loop method).…”

Section: A Supervised Learningmentioning

confidence: 99%

“…The first is field programmable gate arrays or FPGAs. FPGAs have been frequently utilized in neuromorphic systems [86], [169], [192], [194], [200], [202], [206], [207], [217], [481], [489]- [570], [573], [575], [587], [588], [605], [617]- [619], [805], [806] [1106], [1139], [1141]- [1148], [1155]- [1159], [1179]- [1182], [1187]- [1192], [1209]- [1211], [1213], [1214], [1245]- [1248], [1267], [1268], [1277], [1279]- [1282], [1287], [1289], [1293], [1304], [1339]- [1348], …”

Section: A High-levelmentioning

confidence: 99%

See 2 more Smart Citations

A Survey of Neuromorphic Computing and Neural Networks in Hardware

Schuman¹,

Potok²,

Patton³

et al. 2017

Preprint

176

180

View full text Add to dashboard Cite

Neuromorphic computing has come to refer to a variety of brain-inspired computers, devices, and models that contrast the pervasive von Neumann computer architecture. This biologically inspired approach has created highly connected synthetic neurons and synapses that can be used to model neuroscience theories as well as solve challenging machine learning problems. The promise of the technology is to create a brainlike ability to learn and adapt, but the technical challenges are significant, starting with an accurate neuroscience model of how the brain works, to finding materials and engineering breakthroughs to build devices to support these models, to creating a programming framework so the systems can learn, to creating applications with brain-like capabilities. In this work, we provide a comprehensive survey of the research and motivations for neuromorphic computing over its history. We begin with a 35-year review of the motivations and drivers of neuromorphic computing, then look at the major research areas of the field, which we define as neuro-inspired models, algorithms and learning approaches, hardware and devices, supporting systems, and finally applications. We conclude with a broad discussion on the major research topics that need to be addressed in the coming years to see the promise of neuromorphic computing fulfilled. The goals of this work are to provide an exhaustive review of the research conducted in neuromorphic computing since the inception of the term, and to motivate further work by illuminating gaps in the field where new research is needed.

show abstract

Section: Network Modelsmentioning

confidence: 99%

Section: A Supervised Learningmentioning

confidence: 99%

Section: A High-levelmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Neuromorphic Computing and Neural Networks in Hardware

Schuman¹,

Potok²,

Patton³

et al. 2017

Preprint

176

180

View full text Add to dashboard Cite

show abstract

“…Generally, eSNN reported promising results on both large and small datasets, which has motivated an FPGA hardware implementation of the system [91].…”

Section: Taste Recognitionmentioning

confidence: 99%

Evolving spiking neural network—a survey

2013

View full text Add to dashboard Cite

This paper provides a comprehensive literature survey on the evolving Spiking Neural Network (eSNN) architecture since its introduction in 2006 as a further extension of the ECoS paradigm introduced by Kasabov in 1998. We summarize the functioning of the method, discuss several of its extensions and present a number of applications in which the eSNN method was employed. We focus especially on some proposed extensions that allow the processing of spatio-temporal data and for feature and parameter optimisation of eSNN models to achieve better accuracy on classification/prediction problems and to facilitate new knowledge discovery. Finally, some open problems are discussed and future directions highlighted.

show abstract

“…Most of the attention has been focused on: (a) the design of new spiking neuron models; 2-4 (b) information encoding; [5][6][7][8][9] (c) training algorithms; [10][11][12] (d) applications [13][14][15] and (e) hardware implementations. [16][17][18][19] SNNs have the ability to solve real world problems for which no solution is known. Unfortunately, only a small amount of SNNs have knowledge extraction facilities 20 to indicate how the problem was solved and the decision was made.…”

Section: Introductionmentioning

confidence: 99%

Knowledge Extraction From Evolving Spiking Neural Networks With Rank Order Population Coding

Soltic

Kasabov

2010

Int. J. Neur. Syst.

Self Cite

View full text Add to dashboard Cite

This paper demonstrates how knowledge can be extracted from evolving spiking neural networks with rank order population coding. Knowledge discovery is a very important feature of intelligent systems. Yet, a disproportionally small amount of research is centered on the issue of knowledge extraction from spiking neural networks which are considered to be the third generation of artificial neural networks. The lack of knowledge representation compatibility is becoming a major detriment to end users of these networks. We show that a high-level knowledge can be obtained from evolving spiking neural networks. More specifically, we propose a method for fuzzy rule extraction from an evolving spiking network with rank order population coding. The proposed method was used for knowledge discovery on two benchmark taste recognition problems where the knowledge learnt by an evolving spiking neural network was extracted in the form of zero-order Takagi-Sugeno fuzzy IF-THEN rules.

show abstract

FPGA Implementation of an Evolving Spiking Neural Network

Cited by 6 publications

References 8 publications

A Survey of Neuromorphic Computing and Neural Networks in Hardware

A Survey of Neuromorphic Computing and Neural Networks in Hardware

Evolving spiking neural network—a survey

Knowledge Extraction From Evolving Spiking Neural Networks With Rank Order Population Coding

Contact Info

Product

Resources

About