Data Science Training
Standard Techniques and Deep Learning
November 2017


Overview

In 2012, the Harvard Business School called data scientist the sexiest job of the 21st century, and in 2015 McKinsey projected that “by 2018, the U.S. alone may face a 50-60 percent gap between supply and requisite demand of deep analytic talent“. Why has data scientist become a most in-demand job ?
Today massive amounts of data are available in all areas of science, government and industry. Exploited sensibly, these raw data can significantly improve the efficiency of research, services and industries in as many fields as healthcare, engineering, finance, telecommunications or urban developments just to name a few.
How are powerful companies like Google, Facebook, IBM or Apple using data analysis techniques ? What are the most important algorithms to know and how to apply them to your projects ?


Objectives

Learn the top algorithms used in data analysis
Understand how leading companies are using data analysis techniques
Be able to apply data analysis algorithms to real-world datasets


3-Day Program

Lecture 1 - Introduction to Data Science
The slides are available here.
The references are available here.

Lecture 2 - Python
The slides are available here.
Data and coding examples (Python 3) are available here.

Lecture 3 - Graph Science
The slides are available here.
Data and coding examples (Python 3) are available here.

Lecture 4 - Unsupervised Clustering
The slides are available here.
Data and coding examples (Python 3) are available here.

Lecture 5 - SVM Techniques
The slides are available here.
Data and coding examples (Python 3) are available here.

Lecture 6 - Recommender Systems
The slides are available here.
Data and coding examples (Python 3) are available here.

Lecture 7 - Feature Extraction
The slides are available here.
Data and coding examples (Python 3) are available here.

Lecture 8 - Data Visualization
The slides are available here.
Data and coding examples (Python 3) are available here.

Lecture 9 - Introduction to Deep Learning
The slides are available here.

Lecture 10 - Classification with Neural Networks
The slides are available here.
Data and coding examples (Python 2 & 3) are available here.

Lecture 11 - Training Neural Networks
The slides are available here.
Data and coding examples (Python 2 & 3) are available here.

Lecture 12 - TensorFlow
The slides are available here.
Data and coding examples (Python 3) are available here.

Lecture 13 - Convolutional Neural Networks
The slides are available here.
Data and coding examples (Python 3) are available here.

Lecture 14 - Recurrent Neural Networks
The slides are available here.
Data and coding examples (Python 2 & 3) are available here.

Lecture 15 - Reinforcement Learning
The slides are available here.
Data and coding examples (Python 2) are available here.

Lecture 16 - Deep Learning on Graphs
The slides are available here.
Data and coding examples (Python 3) are available here.

Lecture 17 - Conclusion
The slides are available here.


Get the docker image of the course: docker run -d -p 9000:8888 xbresson/ds0.7 (pwd: deeplearning)