Speeding Up Neural Networks for Large Scale Classification using WTA Hashing

In this paper we propose to use the Winner Takes All hashing technique to speed up forward propagation and backward propagation in fully connected layers in convolutional neural networks. The proposed technique reduces significantly the computational complexity, which in turn, allows us to train layers with a large number of kernels with out the associated time penalty. As a consequence we are able to train convolutional neural network on a very large number of output classes with only a small increase in the computational cost. To show the effectiveness of the technique we train a new output layer on a pretrained network using both the regular multiplicative approach and our proposed hashing methodology. Our results showed no drop in performance and demonstrate, with our implementation, a 7 fold speed up during the training.

[1]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[2]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[3]  Brian Kingsbury,et al.  New types of deep neural network learning for speech recognition and related applications: an overview , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[4]  Sartaj Sahni,et al.  Strassen's Matrix Multiplication on GPUs , 2011, 2011 IEEE 17th International Conference on Parallel and Distributed Systems.

[5]  Vincent Vanhoucke,et al.  Improving the speed of neural networks on CPUs , 2011 .

[6]  Berin Martini,et al.  Large-Scale FPGA-based Convolutional Networks , 2011 .

[7]  Fei-Fei Li,et al.  What Does Classifying More Than 10, 000 Image Categories Tell Us? , 2010, ECCV.

[8]  Jay Yagnik,et al.  The power of comparative reasoning , 2011, 2011 International Conference on Computer Vision.

[9]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[10]  Péter Szolgay,et al.  Configurable multilayer CNN-UM emulator on FPGA , 2003 .

[11]  Jonathon Shlens,et al.  Fast, Accurate Detection of 100,000 Object Classes on a Single Machine , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.