Evolving spiking neural networks for taste recognition

Soltic, Snjezana; Wysoski, Simei Gomes; Kasabov, Nikola

doi:10.1109/ijcnn.2008.4634085

Cited by 33 publications

(30 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Other studies have utilised eSNN as a general classification method, e.g. in the context of classifying water and wine samples [70]. The first eSNNs were based on the Thorpe's neural model [78], in which the importance of early spikes (after the onset of a certain stimulus) is boosted called rank-order coding and learning.…”

Section: Evolving Spiking Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Evolving Spiking Neural Networkmentioning

confidence: 99%

“…The classification performance of eSNN was experimentally explored [70,69] based on water and wine samples collected from [8] and [58]. The topology of the model consists of two layers.…”

Section: Taste Recognitionmentioning

confidence: 99%

Evolving spiking neural network—a survey

2013

View full text Add to dashboard Cite

show abstract

“…However, since the algorithm was based on an ES, it was extremely time consuming to train. More recently, an online evolving SNN was implemented [9], which adds a new neuron to the output layer for each sample. If the weights of the new neuron are similar to any of the previously added neurons, then the two neurons are merged.…”

Section: A Training Algorithmsmentioning

confidence: 99%

“…where τ + and τ − were set to 15 ms. The second window (Bi and Poo) was asymmetrical about the time axis and can also be described by (9) and (10), where the parameters τ + and τ − were set to 16.8 and 33.7 ms, respectively [13], [25]. The final window (Gerstner) [49] was an asymmetrically skewed "sinusoidal" shaped window where τ + and τ − were set to 12 and 24 ms, respectively.…”

Section: B Wbc Datasetmentioning

confidence: 99%

SWAT: A Spiking Neural Network Training Algorithm for Classification Problems

Wade

McDaid

Santos

et al. 2010

IEEE Trans. Neural Netw.

170

128

View full text Add to dashboard Cite

Abstract-This paper presents a synaptic weight association training (SWAT) algorithm for spiking neural networks (SNNs). SWAT merges the Bienenstock-Cooper-Munro (BCM) learning rule with spike timing dependent plasticity (STDP). The STDP/BCM rule yields a unimodal weight distribution where the height of the plasticity window associated with STDP is modulated causing stability after a period of training. The SNN uses a single training neuron in the training phase where data associated with all classes is passed to this neuron. The rule then maps weights to the classifying output neurons to reflect similarities in the data across the classes. The SNN also includes both excitatory and inhibitory facilitating synapses which create a frequency routing capability allowing the information presented to the network to be routed to different hidden layer neurons. A variable neuron threshold level simulates the refractory period. SWAT is initially benchmarked against the nonlinearly separable Iris and Wisconsin Breast Cancer datasets. Results presented show that the proposed training algorithm exhibits a convergence accuracy of 95.5% and 96.2% for the Iris and Wisconsin training sets, respectively, and 95.3% and 96.7% for the testing sets, noise experiments show that SWAT has a good generalization capability. SWAT is also benchmarked using an isolated digit automatic speech recognition (ASR) system where a subset of the TI46 speech corpus is used. Results show that with SWAT as the classifier, the ASR system provides an accuracy of 98.875% for training and 95.25% for testing.Index Terms-Automatic speech recognition, BienenstockCooper-Munro, dynamic synapses, spike timing dependent plasticity, spiking neural networks.

show abstract

“…In [5] an evolving SNN (ESNN) was introduced and applied to pattern recognition problems, later this work was extended to speaker authentication tasks and even to audio-visual pattern recognition [10]. A similar spiking neural model was analyzed [7], in which a classification problem for taste recognition was addressed. Based on a simple but efficient neural model, these approaches used the ESNN architecture, which was trained by a fast one-pass learning algorithm.…”

Section: Introductionmentioning

confidence: 99%

Integrated Feature and Parameter Optimization for an Evolving Spiking Neural Network

Schliebs

Defoin-Platel²,

Kasabov

2009

Advances in Neuro-Information Processing

View full text Add to dashboard Cite

Abstract. This study extends the recently proposed Evolving Spiking Neural Network (ESNN) architecture by combining it with an optimization algorithm, namely the Versatile Quantum-inspired Evolutionary Algorithm (vQEA). Following the wrapper approach, the method is used to identify relevant feature subsets and simultaneously evolve an optimal ESNN parameter setting. Applied to carefully designed benchmark data, containing irrelevant and redundant features of varying information quality, the ESNN-based feature selection procedure lead to excellent classification results and an accurate detection of relevant information in the dataset. Redundant and irrelevant features were rejected successively and in the order of the degree of information they contained.

show abstract

Evolving spiking neural networks for taste recognition

Cited by 33 publications

References 21 publications

Evolving spiking neural network—a survey

Evolving spiking neural network—a survey

SWAT: A Spiking Neural Network Training Algorithm for Classification Problems

Integrated Feature and Parameter Optimization for an Evolving Spiking Neural Network

Contact Info

Product

Resources

About