A Spiking Neural Algorithm for Network Flow

dc.contributor.advisorKwisthout, J.H.P.
dc.contributor.advisorRooij van, Iris,
dc.contributor.authorAli, ABDULLAHI
dc.description.abstractIt 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.thesis.facultyFaculteit der Sociale Wetenschappenen_US
dc.thesis.specialisationMaster Artificial Intelligenceen_US
dc.thesis.studyprogrammeArtificial Intelligenceen_US
dc.titleA Spiking Neural Algorithm for Network Flowen_US
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
S4420241, AliA 2018.pdf
528.31 KB
Adobe Portable Document Format