Print Email Facebook Twitter Activating frequencies Title Activating frequencies: Exploring non-linearities in the Fourier domain Author Uijens, Wouter (TU Delft Electrical Engineering, Mathematics and Computer Science; TU Delft Pattern Recognition and Bioinformatics) Contributor van Gemert, Jan (mentor) Reinders, Marcel (graduation committee) Hildebrandt, Klaus (graduation committee) Degree granting institution Delft University of Technology Date 2018-04-13 Abstract Convolutional Neural Networks (CNNs) are achieving state of the art performance in computer vision. One downside of CNNs is their computational complexity. One way to make CNNs more computational efficient is by implementing their convolutions in the frequency domain, using Fast Fourier Transforms (FFTs). This has as a consequence that most computational time in modern CNNs is spent in those FFTs.If all components of the CNN algorithm could be implemented in the frequency domain, it would no longer be necessary to go back at all to the spatial domain. Most components of the CNN do have alternatives that can be implemented in the frequency domain, however one crucial component doesn’t: the activation function. This thesis is the first published study into activation functions in the frequency domain.In this thesis several potential candidates for an activation function that works directly in the frequency domain are studied. Furthermore, some theoretical contributions on this subject are made. Subject Machine LearningFourier TransformActivation Function To reference this document use: http://resolver.tudelft.nl/uuid:b6dfdac6-691d-44a4-bacb-645df5cfdeaf Part of collection Student theses Document type master thesis Rights © 2018 Wouter Uijens Files PDF Thesis_Wouter_Uijens.pdf 1.92 MB Close viewer /islandora/object/uuid:b6dfdac6-691d-44a4-bacb-645df5cfdeaf/datastream/OBJ/view