Efficient Learning Algorithm Using Compact Data Representation in Neural Networks

  • Masaya KibuneEmail author
  • Michael G. Lee
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10635)


Convolutional neural networks have dramatically improved the prediction accuracy in a wide range of applications, such as vision recognition and natural language processing. However the recent neural networks often require several hundred megabytes of memory for the network parameters, which in turn consume a large amount of energy during computation. In order to achieve better energy efficiency, this work investigates the effects of compact data representation on memory saving for network parameters in artificial neural networks while maintaining comparable accuracy in both training and inference phases. We have studied the dependence of prediction accuracy on the total number of bits for fixed point data representation, using a proper range for synaptic weights. We have also proposed a dictionary based architecture that utilizes a limited number of floating-point entries for all the synaptic weights, with proper initialization and scaling factors to minimize the approximation error. Our experiments using a 5-layer convolutional neural network on Cifar-10 dataset have shown that 8 bits are enough for bit width reduction and dictionary based architecture to achieve 96.0% and 96.5% relative accuracy respectively, compared to the conventional 32-bit floating point.


Data representation Bit width reduction Dictionary-based method Uniform/non-uniform initialization Scaling factor 


  1. 1.
    Horowitz, M.: 1.1 computing’s energy problem (and what we can do about it). In: Solid-State Circuits Conference Digest of Technical Papers (ISSCC), pp. 10–14 (2014)Google Scholar
  2. 2.
    Gupta, S., Agrawal, A., Gopalakrishnan, K., Narayanan, P.: Deep learning with limited numerical precision. In: Proceedings of the 32nd International Conference on Machine Learning, pp. 1737–1746 (2015)Google Scholar
  3. 3.
    Moons, B., De Brabandere, B., Van Gool, L., Verhelst, M.: Energy-efficient convnets through approximate computing. In: Applications of Computer Vision (WACV), pp. 1–8 (2016)Google Scholar
  4. 4.
    Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks: training deep neural networks with weights and activations constrained to +1 or −1. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 29, pp. 4107–4115. MIT Press, Cambridge (2016)Google Scholar
  5. 5.
    Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Quantized neural networks: training neural networks with bit width reduction weights and activations (2016). arXiv preprint: arXiv:1609.07061
  6. 6.
    Chen, W., Wilson, J., Tyree, S., Weinberger, K., Chen, Y.: Compressing neural networks with the hashing trick. In: Proceedings of the 32nd International Conference on Machine Learning, pp. 2285–2294 (2015)Google Scholar
  7. 7.
    Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. In: International Conference on Learning Representations (2016)Google Scholar
  8. 8.
    Lin, Z., Courbariaux, M., Memisevic, R., Bengio, Y.: Neural networks with few multiplications (2015). arXiv preprint: arXiv:1510.03009
  9. 9.
    Hashemi, S., Anthony, N., Tann, H., Bahar, R.I., Reda, S.: Understanding the impact of precision quantization on the accuracy and energy of neural networks. In: 2017 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp. 1474–1479 (2017)Google Scholar
  10. 10.
    Cheng, Y., Yu, F.X., Feris, R.S., Kumar, S., Choudhary, A., Chang, S.F.: An exploration of parameter redundancy in deep networks with circulant projections. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2857–2865 (2015)Google Scholar
  11. 11.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105. MIT Press, Cambridge (2012)Google Scholar
  12. 12.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning, pp. 448–456 (2015)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Fujitsu Laboratories of America, Inc.SunnyvaleUSA

Personalised recommendations