Blog
About

45
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Very Efficient Training of Convolutional Neural Networks using Fast Fourier Transform and Overlap-and-Add

      Preprint

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Convolutional neural networks (CNNs) are currently state-of-the-art for various classification tasks, but are computationally expensive. Propagating through the convolutional layers is very slow, as each kernel in each layer must sequentially calculate many dot products for a single forward and backward propagation which equates to \(\mathcal{O}(N^{2}n^{2})\) per kernel per layer where the inputs are \(N \times N\) arrays and the kernels are \(n \times n\) arrays. Convolution can be efficiently performed as a Hadamard product in the frequency domain. The bottleneck is the transformation which has a cost of \(\mathcal{O}(N^{2}\log_2 N)\) using the fast Fourier transform (FFT). However, the increase in efficiency is less significant when \(N\gg n\) as is the case in CNNs. We mitigate this by using the "overlap-and-add" technique reducing the computational complexity to \(\mathcal{O}(N^2\log_2 n)\) per kernel. This method increases the algorithm's efficiency in both the forward and backward propagation, reducing the training and testing time for CNNs. Our empirical results show our method reduces computational time by a factor of up to 16.3 times the traditional convolution implementation for a 8 \(\times\) 8 kernel and a 224 \(\times\) 224 image.

          Related collections

          Author and article information

          Journal
          1601.06815

          Neural & Evolutionary computing, Artificial intelligence

          Comments

          Comment on this article