Projects per year
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 language | English |
|---|---|
| Title of host publication | Database and Expert Systems Applications - DEXA 2024 Workshops |
| Editors | Bernhard Moser, Lukas Fischer, Anna-Christina Glock, Michael Mayr, Sabrina Luftensteiner, Atif Mashkoor, Johannes Sametinger |
| Place of Publication | Cham |
| Publisher | Springer Nature Switzerland |
| Pages | 57-66 |
| Number of pages | 10 |
| ISBN (Print) | 9783031683015 |
| DOIs | |
| Publication status | Published - 2024 |
Publication series
| Name | Communications in Computer and Information Science |
|---|---|
| Volume | 2169 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
Projects
- 1 Active
-
Spike-based Sampling and Learning
Moser, B. (Researcher) & Lunglmayr, M. (PI)
01.01.2023 → 31.12.2026
Project: Funded research › FFG - Austrian Research Promotion Agency
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver