Date(s) - 2018-06-12 - 2018-06-13
09:30 CEST - 17:30 CEST
EMBL Heidelberg, Room 202
Tutors and helpers
Organised by the Bio-IT Project
This two-day course, delivered by experts in programming for data analysis, will teach participants the principle of machine learning and its implementation in R using mlr package. The main goal of
mlr is to provide a unified interface for machine learning tasks as classification, regression, cluster analysis and survival analysis in R.
Sessions will be driven by many practical exercises and case studies. The schedule and course materials will be added here.
Prior to the course, on June 11, 2018, 2:00 PM at Small Operon, an open seminar will be delivered by Prof. Bernd Bischl. **Title TBA**.
This 2-day course will cover the following topics and sessions:
Sessions on Day-1
1. Introduction to Machine Learning, mlr, KNN, and its _application in a biological dataset_
2. Linear models, regression, regularization, and trees
3. Evaluation (train, test, ROC), and its _application to microbiome-based cancer detection_
4. Hands-on session: application on a new dataset (see the prerequisite #3)
Sessions on Day-2
5. Forests and boosting with a demo
6. Tuning and nested resampling with a demo
7. Interpretable machine learning and feature selection
8. Hands-on session: application on the dataset from Session-4
- The course is aimed at participants preferably with some knowledge of statistics and data modeling, and want to learn more about machine learning and its application and implementation through the hands-on sessions and use cases. The participants are expected to understand the concepts described in these materials before the workshop.
- Participants are expected to bring their own laptop with R version >=3.3.2 installed.
- Please create a Kaggle account for the hands-on sessions.
Optional: The participants can have a look at the mlr tutorial to gain a little head-start, but this will be covered in the lectures.
This course will be offered for free to all EMBL members.
The external participants will be charged with a course fee of 100 Euro. The invoice details will be shared via email.
Cancellation and No-Show:
The registration can be canceled for the free of charge until June 2, 2018.
The participants will be charged a cancellation fee (if canceled after June 2, 2018) or no-show fee of 50 Euros. The invoice details will be shared via email.
Course Material / Etherpad
The course material can be accessed via this ownCloud link:
An Etherpad with course notes is here: