Note on Deep Learning

導覽

CNN:

  • 機器視角:長文揭秘圖像處理和卷積神經網絡架構
  • 卷積神經網絡(CNN)新手指南
  • 技术向:一文读懂卷积神经网络CNN
  • Convolutional Neural Net 筆記
  • 卷积神经网络(CNN)学习笔记1:基础入门
  • (GoogleNet)深入卷積
  • How to create filters for Deep Learning CNN's in successive layers in MATLAB?
    1. Randomly assigning weights for the different filters
      1. Jarrett, K., Kavukcuoglu, K. and Lecun, Y., 2009, September. What is the best multi-stage architecture for object recognition?. In 2009 IEEE 12th International Conference on Computer Vision (pp. 2146-2153). IEEE.
      2. Saxe, A., Koh, P.W., Chen, Z., Bhand, M., Suresh, B. and Ng, A.Y., 2011. On random weights and unsupervised feature learning. In Proceedings of the 28th international conference on machine learning (ICML-11) (pp. 1089-1096).
    2. Handcrafting the weights of the different filters to detect specific features during convolution. This approach is not all that interesting in the context of deep learning since it defeats the purpose of learning features without really engineering them!
    3. Learning filter weights using unsupervised training schemes. For example, there are literatures describing the use of auto encoders, deep belief nets, K-means clustering etc. for unsupervised learning of convolution filters.
      1. Masci, J., Meier, U., Cireşan, D. and Schmidhuber, J., 2011, June. Stacked convolutional auto-encoders for hierarchical feature extraction. In International Conference on Artificial Neural Networks (pp. 52-59). Springer Berlin Heidelberg.
      2. Lee, H., Grosse, R., Ranganath, R. and Ng, A.Y., 2009, June. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In Proceedings of the 26th annual international conference on machine learning (pp. 609-616). ACM.
      3. Coates, A., Lee, H. and Ng, A.Y., 2010. An analysis of single-layer networks in unsupervised feature learning. Ann Arbor, 1001(48109), p.2.

Framework 用例

其他應用

近況:

Materials:

Career:

ai
Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License