In this paper, we show the possibility of creating and identifying the features of an artificial neural network (ANN), which consists of mathematical models of biological neurons. The FitzHugh–Nagumo (FHN) system is used as a paradigmatic model demonstrating basic neuron activities. First, in order to reveal how biological neurons can be embedded within an ANN, we train the ANN with nonlinear neurons to solve a basic image recognition problem with an MNIST database; next, we describe how FHN systems can be introduced into this trained ANN. After all, we show that an ANN with FHN systems inside can be successfully trained with improved accuracy comparing with first trained ANN and then with inserted FHN systems. This approach opens up great opportunities in terms of the direction of analog neural networks, in which artificial neurons can be replaced by more appropriate biological ones.
1 February 2025 in Chaos: An Interdisciplinary Journal of Nonlinear Science
This research studies the properties of two coupled Hodgkin–Huxley neurons. The influence of coupling strength as well as individual parameters of the neurons (i.e., initial conditions and external current values) have been studied. A Pearson correlation coefficient is used to estimate the synchrony degree between the neurons. It was found that the two neurons can be synchronized fairly easily in different regimes based on the combination of parameters: for some cases, the neurons are synchronous in a self-oscillating regime, but for other combinations, a single-spike regime becomes prevalent. It was also discovered that the synchronization regime can be controlled both by the external current value of each neuron and the coupling strength value. The obtained results can be profitable for future research of complex networks of artificial neurons.
1 January 2020 in Izvestiya of Saratov University. Physics