Mastering Machine Learning with R - Second Edition

Deep learning resources and advanced methods

One of the more interesting visual tools you can use for both learning and explaining is the interactive widget provided by TensorFlow^TM: http://playground.tensorflow.org/. This tool allows you to explore, or tinker, as the site calls it, the various parameters and how they impact on the response, be it a classification problem or a regression problem. I could spend, well I have spent hours tinkering with it.

Here is an interesting task: create your own experimental design and see how the various parameters affect your prediction.

At this point, it seems that the two fastest growing deep learning open-source tools are TensorFlow^TM and MXNet. I still prefer working with the package we will see, ...