Print Email Facebook Twitter N-shot Training Methodology Title N-shot Training Methodology: For Spiking Neural Networks(SNNs) Author Joshi, Ninad (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor van Leuken, Rene (mentor) Al-Ars, Zaid (graduation committee) Kumar, Sumeet (graduation committee) Zjajo, Amir (graduation committee) Degree granting institution Delft University of Technology Programme Electrical Engineering | Circuits and Systems Date 2019-10-24 Abstract Traditional Artificial Neural Networks(ANNs)like CNNs have shown tremendous opportunities in various domains like autonomous cars, disease diagnosis, etc. Proven learning algorithms like backpropagation help ANNs in achieving higher accuracy. But there is a serious challenge with the increasing popularity of traditional ANNs is of energy consumption and computational complexity. Spiking Neural Networks (SNNs) are considered to be next-generation neural networks that are capable of doing complex deep learning applications at fraction of energy that is needed in current deep learning applications because of its similarity to biological neurons. However, SNN is still not able to match the classification accuracy of ANNs which poses a big challenge for wide acceptance of SNN in various applications as traditional learning methods like backpropagation are not possible in SNN. During training of a neural network the weight matrix is of the highest importance as it eventually decides the trajectory of learning. Currently, one existing solution is to just manually convert ANNs into SNNs to get weight matrix which doesn't focus on getting weight matrix from a small dataset and doesn't consider spiking neuron parameters. We propose a novel N-shot training methodology that is capable of providing a weight matrix for SNN and can give sufficient classification accuracy. The methodology not only provides the weight matrix but can perform training with a very small dataset(up to 1 image per class) and still obtain considerably higher accuracy. For a reduced MNIST dataset, the method can give an accuracy of 71.68% 10 images per class. Subject N-shot LearningSpiking Neural Networks(SNNs))Learning MethodologyNeuromorphic Systems To reference this document use: http://resolver.tudelft.nl/uuid:628a1266-b28e-4e89-a730-fb5e6ffbfc2f Embargo date 2020-10-24 Part of collection Student theses Document type master thesis Rights © 2019 Ninad Joshi Files PDF NinadJoshi_thesis.pdf 3.31 MB Close viewer /islandora/object/uuid:628a1266-b28e-4e89-a730-fb5e6ffbfc2f/datastream/OBJ/view