This is a collections of resources (mostly ipython/jupyter notebooks) for the SJC Feb 2018 ConnectIntensive MLND session.

The master schedule can be found [here](./MLND_ Feb 10 '18 Weekly Schedule.pdf)

• ** Session 1 [February 10, 2018] **
• no session [February 17, 2018] - President's Day
• Session 2 [February 24, 2018]
• Session 3 [March 3, 2018]
• Session 4 [March 10, 2018]
• Session 5 [March 17, 2018]
• Session 6 [March 24, 2018]
• no Session [March 31, 2018] - Easter
• Session 7 [April 7, 2018]
• Session 8 [April 14, 2018]
• Session 9 [April 21, 2018]
• Session 10 [April 28, 2018]
• Session 11 [May 5, 2018]
• Session 12 [May 12, 2018]
• Session 13 [May 19, 2018]
• no Session 1 [May 26, 2018] - Memorial Day
• Session 11 [June 2, 2018]
• Session 12 [June 9, 2018]
• Session 11 [June 16, 2018]

TBD

The IPython/jupyter notebooks are tested with a Python 2.7.11+ interpreter.They also use the following packages:

• numpy
• pandas
• sklearn v0.17, v.018
• matplotlib

Additional resources from the relevant Udacity repositories are referenced in some of the notebooks and the MLND projects repository should be available on your local storage device.

Please verify that these libraries are installed in your local python environment before attempting to load and run any of the notebooks.

If you are enrolled in the Feb 2018 session of ConnectIntensive MLND, you may download or clone the repository for your use.

If you are not enrolled but wish to take a closer look at the materials here, please send me an email telling me who you are and your reason for requesting access to these materials.

• MLND projects
• Deep Learning - the link to the online class is here

• General Machine Learning

  • Nando de Freitas, Oxford University The link is to a website for a class on Machine Learning (including deep learning) taught by Nando de Freitas. There are slides, and links to YouTube videos. The videos are full-length (ca. 1 hr) and there are many of them, so not a quick introduction. If you have the time, could help cement some of the concepts you are learning in the ML ND.

• Deep Learning

  • Fei-Fei-Li, Stanford University The link is to the first video lecture; there are quite a few more. This is a class on using Deep Learning for Image Recognition (CS231n). The schedule for the course (Winter 2016. so a bit dated, but excellent content) is here

• Reinforcement Learning

  • David Silver, Oxford University This is a set of video lectures on Reinforcement Learning by D Silver (thanks Nick!) available on Youtube that give a broader introduction to the subject. There are 10 lectures, 1.5 hrs each. If you want to learn more about RL, this may be a good place to start. There is also a website with the slides from the videos here