Solving the Linearly Inseparable XOR Problem with Spiking Neural Networks
Wall, J. and Reljan-Delaney, M. 2017. Solving the Linearly Inseparable XOR Problem with Spiking Neural Networks . SAI Computing Conference 2017. London, UK 18 - 20 Jul 2017 IEEE. https://doi.org/10.1109/SAI.2017.8252173
|Wall, J. and Reljan-Delaney, M.
Spiking Neural Networks (SNN) are third generation neural networks and are considered to be the most biologically plausible so far. As a relative newcomer to the field of artificial learning, SNNs are still exploring their own capabilities, as well as dealing with the singular challenges that arise from attempting to be computationally applicable and biologically accurate. This paper explores the possibility of a different approach to solving linearly inseparable problems by using networks of spiking neurons. To this end two experiments were conducted. The first experiment was an attempt in creating a spiking neural network that would mimic the functionality of logic gates. The second experiment relied on the addition of receptive fields in order to filter the input. This paper demonstrates that a network of spiking neurons utilizing receptive fields or routing can successfully solve the XOR linearly inseparable problem.
|SAI Computing Conference 2017
|Accepted author manuscript
|11 Jan 2018
|Publication process dates
|04 Oct 2019
|Proceedings of Computing Conference 2017
|Digital Object Identifier (DOI)
|Web address (URL)
|© 2017 IEEE
|Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
17views this month
10downloads this month