Image processing using self-learning fuzzy spiking neural network in the presence of overlapping classes

Bodyanskiy, Yevgeniy; Dolotov, Artem

doi:10.1109/bec.2008.4657517

Cited by 10 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These two concepts may seem similar at first, but fuzzy logic assigns a value to a set based on the membership functions, while DoBs are adjusted incrementally depending on their spiking activity in response to the samples from different classes without any membership functions or fuzzy rules. There are some methods which combine the concept of fuzzy logic with spiking neural networks [29][30] [31][32] [33]. These approaches employ the idea of fuzzy logic to create frequency-based receptive fields for neurons [29] [30], encode the input data into spike patterns [31] [32], or cluster the input patterns [33].…”

Section: Discussionmentioning

confidence: 99%

Assembly-based STDP: A New Learning Rule for Spiking Neural Networks Inspired by Biological Assemblies

Saranirad

Dora

McGinnity

et al. 2022

2022 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Spiking Neural Networks (SNNs), An alternative to sigmoidal neural networks, include time into their operations using discrete signals called spikes. Employing spikes enables SNNs to mimic any feedforward sigmoidal neural network with lower power consumption. Recently a new type of SNN has been introduced for classification problems, known as Degree of Belonging SNN (DoB-SNN). DoB-SNN is a two-layer spiking neural network that shows significant potential as an alternative SNN architecture and learning algorithm. This paper introduces a new variant of Spike-Timing Dependent Plasticity (STDP), which is based on the assembly of neurons and expands the DoB-SNN's training algorithm for multilayer architectures. The new learning rule, known as assembly-based STDP, employs trained DoBs in each layer to train the next layer and build strong connections between neurons from the same assembly while creating inhibitory connections between neurons from different assemblies in two consecutive layers. The performance of the multilayer DoB-SNN is evaluated on five datasets from the UCI machine learning repository. Detailed comparisons on these datasets with other supervised learning algorithms show that the multilayer DoB-SNN can achieve better performance on 4/5 datasets and comparable performance on 5th when compared to multilayer algorithms that employ considerably more trainable parameters.

show abstract

Section: Discussionmentioning

confidence: 99%

Assembly-based STDP: A New Learning Rule for Spiking Neural Networks Inspired by Biological Assemblies

Saranirad

Dora

McGinnity

et al. 2022

2022 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…In order to avoid a negative spike that appears as a response to the relay resetting, a usual diode is added next to the derivative unit. The diode is defined by the following function: (8) In [10], the mechanism of threshold detection behavior and neuron firing process were only described. Here we extend this approach to capture refractoriness of spiking neuron.…”

Section: Layers Of Spiking Neuronsmentioning

confidence: 99%

“…Moreover, being more realistic models of biological neural systems than artificial neural networks of the previous generations [4,5], spiking neural networks present another step of computational intelligence paradigm evolving toward biologically plausible computing [6]. Hybrid intelligent systems designed on the basis of self-learning spiking neural networks and fuzzy clustering approaches were shown to be successfully applied for data clustering in the presence of overlapping classes [7][8][9]. Another area where self-learning spiking neural networks and hybrid systems based on them can be successfully used is a hierarchical clustering.…”

Section: Introductionmentioning

confidence: 99%

A Multilayered Self-Learning Spiking Neural Network and its Learning Algorithm Based on ‘Winner-Takes-More’ Rule in Hierarchical Clustering

Bodyanskiy¹,

Dolotov²

2009

Scientific Journal of Riga Technical University. Computer Sciences

View full text Add to dashboard Cite

A Multilayered Self-Learning Spiking Neural Network and its Learning Algorithm Based on ‘Winner-Takes-More’ Rule in Hierarchical ClusteringThis paper introduces architecture of multilayered selflearning spiking neural network for hierarchical data clustering. It consists of the layer of population coding and several layers of spiking neurons. Contrary to originally suggested multilayered spiking neural network, the proposed one does not require a separate learning algorithm for lateral connections. Irregular clusters detecting capability is achieved by improving the temporal Hebbian learning algorithm. It is generalized by replacing ‘Winner-Takes-All’ rule with ‘Winner-Takes-More’ one. It is shown that the layer of receptive neurons can be treated as a fuzzification layer where pool of receptive neurons is a linguistic variable, and receptive neuron within a pool is a linguistic term. The network architecture is designed in terms of control systems theory. Using the Laplace transform notion, spiking neuron synapse is presented as a second-order critically damped response unit. Spiking neuron soma is modeled on the basis of bang-bang control systems theory as a threshold detection system. Simulation experiment confirms that the proposed architecture is effective in detecting irregular clusters.

show abstract

“…Some attention was paid to a task of these missing values recovery [21][22][23]. The most effective approaches for this specific case were methods based on Computational Intelligence (mathematical tools of soft computing) [24][25][26][27][28][29][30] and primarily artificial neural networks [31][32][33][34][35][36]. Besides that, some widely known approaches to gaps' recovery and traditional clustering algorithms can be applied only in instances when an initial data table is given a priori and a number of its rows and columns can't be changed during data processing.…”

Section: Introductionmentioning

confidence: 99%

Fuzzy Clustering Data Arrays with Omitted Observations

Hu¹,

Bodyanskiy²,

Tyshchenko³

et al. 2017

IJISA

View full text Add to dashboard Cite

show abstract

Image processing using self-learning fuzzy spiking neural network in the presence of overlapping classes

Abstract: Architecture of self-learning fuzzy spiking neural network that belongs to a new type of hybrid intelligence systems is proposed. Both crisp and fuzzy clustering modes are described. Results of image processing in the presence of overlapping classes are presented.

Cited by 10 publications

References 6 publications

Assembly-based STDP: A New Learning Rule for Spiking Neural Networks Inspired by Biological Assemblies

Assembly-based STDP: A New Learning Rule for Spiking Neural Networks Inspired by Biological Assemblies

A Multilayered Self-Learning Spiking Neural Network and its Learning Algorithm Based on ‘Winner-Takes-More’ Rule in Hierarchical Clustering

Fuzzy Clustering Data Arrays with Omitted Observations

Contact Info

Product

Resources

About