Print Email Facebook Twitter Supervised Learning in Spiking Neural Networks Title Supervised Learning in Spiking Neural Networks Author Büller, Bas (TU Delft Aerospace Engineering) Contributor de Croon, Guido (mentor) Paredes Valles, Federico (graduation committee) Degree granting institution Delft University of Technology Programme Aerospace Engineering Date 2020-05-25 Abstract Spiking neural networks are notoriously hard to train because of their complex dynamics and sparse spiking signals. However, in part due to these properties, spiking neurons possess high computa- tional power and high theoretical energy efficiency. This thesis introduces an online, supervised, and gradient-based learning algorithm for spiking neural networks. It is shown how gradients of temporal signals that influence spiking neurons can be calculated online as an eligibility trace. The trace rep- resents the temporal gradient as a single scalar value and is recursively updated at each consecutive iteration. Moreover, the learning method uses approximate error signals to simplify their calculation and make the error calculation compatible with online learning. In several experiments, it is shown that the algorithm can solve spatial credit assignment problems with short-term temporal dependencies in deep spiking neural networks. Potential approaches for improving the algorithm’s performance on long-term temporal credit assignment problems are also discussed. Besides the research on spiking neural networks, this thesis includes an in-depth literature study on the topics of neuromorphic computing and deep learning, as well as extensive evaluations of several learning algorithms for spiking neural networks Subject Spiking Neural Networks(SNNs))Supervised LearningOnline learningNeuromorphic computing To reference this document use: http://resolver.tudelft.nl/uuid:256f7044-862d-4b53-b395-973dadbb7a00 Coordinates 51.9899, 4.3753 Part of collection Student theses Document type master thesis Rights © 2020 Bas Büller Files PDF msc_thesis_bas_buller_4166566.pdf 4.69 MB Close viewer /islandora/object/uuid:256f7044-862d-4b53-b395-973dadbb7a00/datastream/OBJ/view