A Spiking Neural Algorithm for Network Flow
| dc.contributor.advisor | Kwisthout, J.H.P. | |
| dc.contributor.advisor | Rooij van, Iris, | |
| dc.contributor.author | Ali, ABDULLAHI | |
| dc.date.issued | 2019-06-05 | |
| dc.description.abstract | It is not clear what the potential is of neuromorphic hardware beyond machine learning and neuroscience. In this project, a problem is investigated that is inherently difficult to fully implement in neuromorphic hardware by introducing a new machine model in which a conventional Turing machine and neuromorphic oracle work together to solve such types of problems. A lattice of complexity classes is introduced: CSNN(RS), in which a neuromorphic oracle is consulted using only resources at most RS. We show that the P-complete MAX NETWORK FLOW problem is in LSNN(O(n);O(n);O(n)) for graphs with n edges. A modified variant of this algorithm is implemented on the Intel Loihi chip; a neuromorphic manycore processor developed by Intel Labs. We show that by off-loading the search for augmenting paths to the neuromorphic processor we can get energy efficiency gains, while not sacrificing runtime resources. This result demonstrates how P-complete problems can be mapped on neuromorphic architectures in a theoretically and potentially practically efficient manner. | en_US |
| dc.identifier.uri | https://theses.ubn.ru.nl/handle/123456789/10330 | |
| dc.language.iso | en | en_US |
| dc.thesis.faculty | Faculteit der Sociale Wetenschappen | en_US |
| dc.thesis.specialisation | Master Artificial Intelligence | en_US |
| dc.thesis.studyprogramme | Artificial Intelligence | en_US |
| dc.thesis.type | Master | en_US |
| dc.title | A Spiking Neural Algorithm for Network Flow | en_US |
Files
Original bundle
1 - 1 of 1