Skip to main navigation Skip to search Skip to main content

On the Solvability of the XOR Problem by Spiking Neural Networks

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

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.
Original languageEnglish
Title of host publicationDatabase and Expert Systems Applications - DEXA 2024 Workshops
EditorsBernhard Moser, Lukas Fischer, Anna-Christina Glock, Michael Mayr, Sabrina Luftensteiner, Atif Mashkoor, Johannes Sametinger
Place of PublicationCham
PublisherSpringer Nature Switzerland
Pages57-66
Number of pages10
ISBN (Print)9783031683015
DOIs
Publication statusPublished - 2024

Publication series

NameCommunications in Computer and Information Science
Volume2169 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Fields of science

  • 202017 Embedded systems
  • 202036 Sensor systems
  • 102019 Machine learning
  • 202 Electrical Engineering, Electronics, Information Engineering
  • 202015 Electronics
  • 202022 Information technology
  • 202037 Signal processing

JKU Focus areas

  • Digital Transformation

Cite this