METHOD OF CONSTRUCTING A NEURAL NETWORK BASED ON BIOMATERIALS

The modern approach to building neural networks evolves and continues to develop in improving the mathematical model of neuron functioning, which leads to new differences from real biological analogues, since a highly simplified model of the basic element (neuron) is used to model modern neural networks. The purpose of this work is to calculate the information capacity of a neural network built on a biological neuron, to provide evidence of the prospects for studying methods for building a neural network using biological neurons. A mathematical description of the main structural elements of a biological neural network is given: neurons, axons and dendrites and neurotransmitters, as key parameters for data exchange between neurons. It is shown that biological neural networks, unlike artificial ones, require up to 6000 times less energy for computing work and lower production costs. Artificial neural networks are an expensive technology due to the high costs of training and development, despite the fact that many manufacturers mass-produce integrated circuits. It was found that using a biochip it is possible to reduce these costs many times, because living cells learn much faster, are distinguished by high neuroplasticity. But in creating a neural network based on a biological neuron, problems were noted: maintaining the vital activity of a biological neural network; synthesis of cells for the system; as well as integration of biomaterials and a processor. In the work, the information capacity of a biological neural network was calculated and compared with different types of artificial ones (unidirectional sigmoid neural network, radical neural network, recurrent neural networks, recurrent networks based on a perceptron, neural networks with self-organization based on competition, fuzzy neural networks). The results of experimental calculations showed that a neural network built on biomaterials is 92% higher in information capacity compared to a computer model, which indicates the achievement of the goals set in the work.