A Fourier domain acceleration framework for convolutional neural networks
Authors:
- Jinhua LinJLJinhua Lin
- Lin MaLMLin Ma
- Yu YaoYYYu Yao
- 1 October 2019
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 364, 254-268
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (51705032)
- National High-tech R&D Program (2014AA7031010B)
This publication has 21 references indexed in Scilit:
- Efficient Training of Convolutional Deep Belief Networks in the Frequency Domain for Application to High-Resolution 2D and 3D ImagesNeural Computation, 2015
- Learning to Rank Using User Clicks and Visual Features for Image RetrievalIEEE Transactions on Cybernetics, 2014
- Click Prediction for Web Image Reranking Using Multimodal Sparse CodingIEEE Transactions on Image Processing, 2014
- Approximation results for neural network operators activated by sigmoidal functionsNeural Networks, 2013
- PSBLASACM Transactions on Mathematical Software, 2000
- Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theoryNeural Networks, 1991
- Fast fourier transforms: A tutorial review and a state of the artSignal Processing, 1990
- Constructive approximations for neural networks by sigmoidal functionsProceedings of the IEEE, 1990
- Gaussian elimination is not optimalNumerische Mathematik, 1969
- An algorithm for the machine calculation of complex Fourier seriesMathematics of Computation, 1965