Kolmogorov–Arnold neural network for identification of functional groups from FTIR spectra

New architecture of a deep neural network for identification of functional groups of molecules based on FTIR spectra is presented. The architecture employs the innovative Kolmogorov–Arnold layers. Instead of a single weight, each input in neurons belonging to these layers, possesses an independent learnable activation function. The article analyzes the quality of the neural network prediction for convolutional network containing Kolmogorov–Arnold layers in comparison with a classic convolutional neural network for 22 functional groups. The obtained results are compared with the results available from other studies.