Show simple item record

AuthorKiranyaz, Mustafa Serkan
AuthorMalik J.
AuthorAbdallah H.B.
AuthorInce T.
AuthorIosifidis A.
AuthorGabbouj M.
Available date2022-04-26T12:31:18Z
Publication Date2021
Publication NameNeural Computing and Applications
ResourceScopus
Identifierhttp://dx.doi.org/10.1007/s00521-020-05543-w
URIhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85098700454&doi=10.1007%2fs00521-020-05543-w&partnerID=40&md5=59ef232f96686a195d312b0565f33385
URIhttp://hdl.handle.net/10576/30588
AbstractThe recently proposed network model, Operational Neural Networks (ONNs), can generalize the conventional Convolutional Neural Networks (CNNs) that are homogenous only with a linear neuron model. As a heterogenous network model, ONNs are based on a generalized neuron model that can encapsulate any set of non-linear operators to boost diversity and to learn highly complex and multi-modal functions or spaces with minimal network complexity and training data. However, the default search method to find optimal operators in ONNs, the so-called Greedy Iterative Search (GIS) method, usually takes several training sessions to find a single operator set per layer. This is not only computationally demanding, also the network heterogeneity is limited since the same set of operators will then be used for all neurons in each layer. To address this deficiency and exploit a superior level of heterogeneity, in this study the focus is drawn on searching the best-possible operator set(s) for the hidden neurons of the network based on the ?Synaptic Plasticity? paradigm that poses the essential learning theory in biological neurons. During training, each operator set in the library can be evaluated by their synaptic plasticity level, ranked from the worst to the best, and an ?elite? ONN can then be configured using the top-ranked operator sets found at each hidden layer. Experimental results over highly challenging problems demonstrate that the elite ONNs even with few neurons and layers can achieve a superior learning performance than GIS-based ONNs and as a result, the performance gap over the CNNs further widens.
Languageen
PublisherSpringer Science and Business Media Deutschland GmbH
SubjectComplex networks
Convolutional neural networks
Heterogeneous networks
Iterative methods
Learning systems
Mathematical operators
Personnel training
Biological neuron
Generalized neuron
Heterogenous network
Learning performance
Multi modal function
Network heterogeneity
Synaptic plasticity
Training sessions
Neurons
TitleExploiting heterogeneity in operational neural networks by synaptic plasticity
TypeArticle
Pagination7997-8015
Issue Number13
Volume Number33
dc.accessType Abstract Only


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record