On the Solvability of the {XOR} Problem by Spiking Neural Networks

TL;DR

This paper investigates how spiking neural networks can solve the XOR problem using minimal configurations, focusing on hyperparameters and encoding strategies to achieve sparse solutions with only two hidden neurons.

Contribution

It demonstrates that specific hyperparameter choices enable minimal spiking neural networks to solve XOR and related logical problems efficiently.

Findings

Reset-to-mod mechanism enables sparse solutions.

Two hidden neurons suffice for XOR with proper parameters.

Encoding and hyperparameters critically influence solvability.

Abstract

The linearly inseparable XOR problem and the related problem of representing binary logical gates is revisited from the point of view of temporal encoding and its solvability by spiking neural networks with minimal configurations of leaky integrate-and-fire (LIF) neurons. We use this problem as an example to study the effect of different hyper parameters such as information encoding, the number of hidden units in a fully connected reservoir, the choice of the leaky parameter and the reset mechanism in terms of reset-to-zero and reset-by-subtraction based on different refractory times. The distributions of the weight matrices give insight into the difficulty, respectively the probability, to find a solution. This leads to the observation that zero refractory time together with graded spikes and an adapted reset mechanism, reset-to-mod, makes it possible to realize sparse solutions of a minimal configuration with only two neurons in the hidden layer to resolve all binary logic gate constellations with XOR as a special case.