Skip to content

lsy323/Duke-Tsinghua-MLSS-2017

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

37 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Duke-Tsinghua Machine Learning Summer School (MLSS) 2017

Welcome to the Duke-Tsinghua Machine Learning Summer School 2017! This repository contains the lecture materials for the TensorFlow Workshops, as well as the homework assignment for the Introduction to Multilayer Perceptrons and Convolutional Neural Networks lectures.

Before you arrive

Most of the content for this workshop is organized into Jupyter IPython notebooks. Please go through the notebooks labeled 00[ABC] before you come to the Duke-Kunshan campus. These notebooks will walk you through the steps of installing Python and TensorFlow, as well as give a condensed tutorial on Python coding environments and Git. Some basic understanding of coding in Python is assumed, so if you're new or a little rusty, brushing up before the class is recommended.

By the end of the 3 pre-requisite notebooks, you should have a local copy of your fork of this repository on the laptop you intend to bring to the MLSS, know how to open a notebook in Jupyter, and while you don't need to go through the material itself, be able to run all cells ("Cell > Run all") within 01A_TensorFlow_Basics.ipynb without errors. If you have any difficulties with these steps, there will be office hours at the start of the MLSS to help sort out any difficulties.

Acknowledgements

Thank you to David Carlson, Alex Lew, Shariq Iqbal, Daniel Salo, and Greg Spell for contributions, testing, and feedback.

Obligatory disclaimer: This is not an official Google Product. Any statements or opinions are mine and do not necessarily represent Google in any way.

About

Duke-Tsinghua Machine Learning Summer School 2017

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%