CC BYSerkan KiranyazJunaid MalikAlexandros IosifidisMoncef GabboujHabib Ben AbdallahTurker Ince2025-06-192025-06-192021-01-040941-06431433-305810.1007/s00521-020-05543-w10.48550/arxiv.2009.08934https://ror.circle-u.eu/handle/123456789/1222026<jats:title>Abstract</jats:title><jats:p>The 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<jats:italic>any</jats:italic>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.</jats:p>OPENFOS: Computer and information sciencesComputer Science - Machine LearningIterative methodsBiological neuronComplex networksMachine Learning (stat.ML)Multi modal function530113Heterogenous networkSynaptic plasticityMachine Learning (cs.LG)Statistics - Machine LearningGeneralized neuronNetwork heterogeneityNeural and Evolutionary Computing (cs.NE)Mathematical operatorsTraining sessionsNeuronsLearning systemsLearning performanceComputer Science - Neural and Evolutionary Computing113 Computer and information sciences004Convolutional neural networksHeterogeneous networksPersonnel trainingpublication0301 basic medicine02 engineering and technology03 medical and health sciences0202 electrical engineering, electronic engineering, information engineeringdoi_dedup___:de21c6425b256322831536e3885adb5ehttp://arxiv.org/abs/2009.0893410576/30588