{"id":8352,"date":"2017-01-13T09:00:44","date_gmt":"2017-01-13T14:00:44","guid":{"rendered":"https:\/\/blogs.mathworks.com\/pick\/?p=8352"},"modified":"2018-09-14T06:50:47","modified_gmt":"2018-09-14T10:50:47","slug":"deep-learning-in-11-lines","status":"publish","type":"post","link":"https:\/\/blogs.mathworks.com\/pick\/2017\/01\/13\/deep-learning-in-11-lines\/","title":{"rendered":"Deep Learning in 11 Lines"},"content":{"rendered":"
\n

Jiro<\/a>‘s pick this week is Deep Learning in 11 Lines of MATLAB Code<\/a> by the MathWorks Deep Learning Toolbox Team<\/a>.<\/p>\n

This is for anyone who would like to dabble in deep learning with minimal effort. There’s also a short video<\/a> of this in action by one of our senior developers. Note that this sample code requires R2016b or newer, the Deep Learning Toolbox<\/a>, and the Image Processing Toolbox<\/a>. Deep Learning Toolbox is a must to use the trained network, but Image Processing Toolbox is used for image resizing in this example. In addition, you need to download\/install the freely available packages for connecting to a webcam<\/a> and a pre-trained convolutional neural network (CNN) called AlexNet<\/a>. Both of these can be easily obtained from the Add-On Explorer<\/a>.<\/p>\n

With R2016b, you get some really nice features in the area of deep learning.<\/p>\n

\n
    \n
  1. CNNs used to require a supported GPU, but now you can run a trained network to extract features, make predictions, and classify on a CPU. GPU is still recommended for a much better performance.<\/li>\n
  2. Training a network is a lot of work and time-consuming. Now, you can download a pre-trained network, called AlexNet, to extract features or to adapt to your own problem set, which is referred to as transfer learning.<\/li>\n<\/ol>\n<\/div>\n

    Just as this entry promises, I was able to do some deep learning on a live image coming in from my webcam, just in 11 lines of MATLAB code.<\/p>\n

    \"\" <\/p>\n

    Seems like I have a coffee mug! :)<\/p>\n

    Comments<\/b><\/p>\n

    Give it a try and let us know what you think here<\/a> or leave a comment<\/a> for the Deep Learning Team.<\/p>\n