Applied machine-learning for science

💻 Material for a course on applied machine-learning for scientists taught at EPFL in spring 2018.

Outline

The course consists of six two hour lectures, followed by one hour to discuss the week's homework assignment. Followed by a final project on real world data.

• Intro and Model Performance
  • slides notebook exercise
• Tree based models
  • slides notebook exercise
• Neural Networks
  • slides exercise
• Feature engineering
• Embeddings and pretrained networks
• Interpretability

Run in the cloud

You can run the notebooks from this repository from your browser without installing anything. To do so click the badge below.

This is good if you want to try out something but mybinder.org makes it a bit difficult to save your work so I recommend you still install things locally.

Technicalities, installing, running code

All the code will be written in python. We will make use of the scientific python stack:

• python v3.6
• numpy v1.12.1
• scikit-learn v0.19
• keras
• matplotlib v2.x.x
• jupyter

All work submitted for credit has to run with these dependencies only.

Instructions on installing on Windows, mac and linux.

Books

There are many good books, lecture courses and videos out there.

• ESL, ISL
• Introduction to machine-learning with python
• COMS W4995 Applied Machine Learning Spring 2018
• EE-559 – Deep Learning