Relaxation autowaves in a bi-local neuron model

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.

Download Full-text

Recurrent Multiplicative Neuron Model Artificial Neural Network for Non-linear Time Series Forecasting

Neural Processing Letters ◽

10.1007/s11063-014-9342-0 ◽

2014 ◽

Vol 41 (2) ◽

pp. 249-258 ◽

Cited By ~ 24

Author(s):

Erol Egrioglu ◽

Ufuk Yolcu ◽

Cagdas Hakan Aladag ◽

Eren Bas

Keyword(s):

Neural Network ◽

Time Series ◽

Artificial Neural Network ◽

Neuron Model ◽

Linear Time ◽

Time Series Forecasting ◽

Non Linear ◽

Artificial Neural

Download Full-text

Digital Implementation of the Two-Compartmental Pinsky–Rinzel Pyramidal Neuron Model

IEEE Transactions on Biomedical Circuits and Systems ◽

10.1109/tbcas.2017.2753541 ◽

2018 ◽

Vol 12 (1) ◽

pp. 47-57 ◽

Cited By ~ 7

Author(s):

Elahe Rahimian ◽

Soheil Zabihi ◽

Mahmood Amiri ◽

Bernabe Linares-Barranco

Keyword(s):

Pyramidal Neuron ◽

Neuron Model ◽

Digital Implementation

Download Full-text

COMPLEX BIFURCATION STRUCTURES IN THE HINDMARSH–ROSE NEURON MODEL

International Journal of Bifurcation and Chaos ◽

10.1142/s0218127407018877 ◽

2007 ◽

Vol 17 (09) ◽

pp. 3071-3083 ◽

Cited By ~ 71

Author(s):

J. M. GONZÀLEZ-MIRANDA

Keyword(s):

Phase Diagram ◽

Bifurcation Diagram ◽

Parameter Space ◽

Neuron Model ◽

Two Dimensional ◽

Dimensional Parameter ◽

Rapid Responses ◽

Bifurcation Structures

The results of a study of the bifurcation diagram of the Hindmarsh–Rose neuron model in a two-dimensional parameter space are reported. This diagram shows the existence and extent of complex bifurcation structures that might be useful to understand the mechanisms used by the neurons to encode information and give rapid responses to stimulus. Moreover, the information contained in this phase diagram provides a background to develop our understanding of the dynamics of interacting neurons.

Download Full-text