On the Solvability of the {XOR} Problem by Spiking Neural Networks
Authors:
- Bernhard A. MoserBMBernhard A. Moser
- Michael LunglmayrMLMichael Lunglmayr
Preprint
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.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Spiking neural networks in the Alexiewicz topology: A new perspective on analysis and error boundsNeurocomputing, 2024
- Training Spiking Neural Networks Using Lessons From Deep LearningProceedings of the IEEE, 2023
- A Survey of Encoding Techniques for Signal Processing in Spiking Neural NetworksNeural Processing Letters, 2021
- Revisiting the XOR problem: a neurorobotic implementationNeural Computing and Applications, 2019
- XOR learning by spiking neural network with infrared communications2018
- Experimental Spiking Neural Network: Solving the XOR Paradigm with Metaheuristics2018
- The Deep Learning Revolution2018
- Fast Sigmoidal Networks via Spiking NeuronsNeural Computation, 1997
- The impulses produced by sensory nerve endingsThe Journal of Physiology, 1926
- Mengen konvexer K rper, die einen gemeinsamen Punkt enthaltenMathematische Annalen, 1921