High-dimensional neural-network artificial intelligence capable of quick learning to recognize a new smell, and gradually expanding the database

We demonstrate that classical quadratic forms are not able to solve the problem of recognizing high-dimensional images. The “deep” Galushkin-Hinton neural networks can solve the problem of high-dimensional image recognition, but their training has exponential computational complexity. It is technically impossible to train and retrain a “deep” neural network rapidly. For mobile “artificial nose” systems we proposed to employ a number of “wide” neural networks trained in accordance with (GOST R 52633.5-2011). This standardized learning algorithm has a linear computational complexity, i.e. for each new smell image a time of about 0.3 seconds is sufficient for creating and training a new neural network with 2024 inputs and 256 outputs. This leads to the possibility of the rapid training of the artificial intelligence “artificial nose” and a gradual expansion of its database consisting of 10 000 or more trained artificial neural networks.