Higher Order and Long-Range Synchronization Effects for Classification and Computing in Oscillator-Based Spiking Neural Networks
This work addresses the need for enhanced computational capabilities in spiking neural networks, particularly for reservoir computing and analog operations, though it appears incremental in applying known synchronization effects to new contexts.
The researchers tackled the problem of increasing the number of synchronous states in oscillator-based spiking neural networks for classification and computing, achieving up to 150 possible states in models and demonstrating applications like image recognition and multiplication.
In the circuit of two thermally coupled VO2 oscillators, we studied a higher order synchronization effect, which can be used in object classification techniques to increase the number of possible synchronous states of the oscillator system. We developed the phase-locking estimation method to determine the values of subharmonic ratio and synchronization effectiveness. In our experiment, the number of possible synchronous states of the oscillator system was twelve, and subharmonic ratio distributions were shaped as Arnold's tongues. In the model, the number of states may reach the maximum value of 150 at certain levels of coupling strength and noise. The long-range synchronization effect in a one-dimensional chain of oscillators occurs even at low values of synchronization effectiveness for intermediate links. We demonstrate a technique for storing and recognizing vector images, which can used for reservoir computing. In addition, we present the implementation of analog operation of multiplication, the synchronization based logic for binary computations, and the possibility to develop the interface between spike neural network and a computer. Based on the universal physical effects, the high order synchronization can be applied to any spiking oscillators with any coupling type, enhancing the practical value of the presented results to expand spike neural network capabilities.