FitzHugh--Nagumo systems in trainable artificial neural network
Nadezhda Semenova1;
1Saratov State University, Saratov, Russia
Abstract
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 paradigmatic model demonstrating basic neuron activity. 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 MNIST database; and 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 with then inserted FHN systems. This approach opens great opportunities in terms of the direction of analog neural networks, in which artificial neurons can be replaced by more appropriate biological ones. Also, we show how this approach can be applied to time-dependent tasks and show the analogue of recurrent neural network.
This work was supported by the Russian President scholarship SP-749.2022.5.
Speaker
Nadezhda Semenova
Saratov State University
Russia
Discussion
Ask question
