Recurrent Spectral Network (RSN): shaping the basin of attraction of a discrete map to reach automated classification
This work presents a new approach to automated classification, potentially useful for domains like image processing, but it appears incremental as it builds on existing dynamical systems concepts.
The authors introduced the Recurrent Spectral Network (RSN), a novel classification method that uses a trained dynamical system to steer data items toward distinct attractors, achieving successful results on a test model and a standard image dataset.
A novel strategy to automated classification is introduced which exploits a fully trained dynamical system to steer items belonging to different categories toward distinct asymptotic attractors. These latter are incorporated into the model by taking advantage of the spectral decomposition of the operator that rules the linear evolution across the processing network. Non-linear terms act for a transient and allow to disentangle the data supplied as initial condition to the discrete dynamical system, shaping the boundaries of different attractors. The network can be equipped with several memory kernels which can be sequentially activated for serial datasets handling. Our novel approach to classification, that we here term Recurrent Spectral Network (RSN), is successfully challenged against a simple test-bed model, created for illustrative purposes, as well as a standard dataset for image processing training.