A tour of machine learning - classification

Goal

This one-day workshop aims at transforming your keen interest into the workings of machine learning algorithms into practical knowledge on how to build accurate predictive models, mainly focussed on classification models.

Summary

Machine learning has become ubiquitous in biotechnology (as in many other fields), fueled largely by the increasing availability and amount of data. Learning algorithms can figure out how to perform important tasks by generalizing examples. Typical applications are diagnoses/prognoses, gene/protein annotation, drug design, image recognition, text mining and many others. However, building successful machine learning models requires a substantial amount of “black art” that is hard to find in textbooks. This course is an interactive Jupyter Notebook (Python) that will teach you how to build successful machine learning models. No background in machine learning is assumed, just a keen interest.

Requirements

Models are build in the Python programming language​. 

Topics

  • ​What is learning by example ?
  • Feature engineering
  • Model training/optimization/evaluation
  • Current state of the art

Topics

  • ​Python Numpy/Pandas​

​​​​​​​

Dates:

12 June 2018 from 9h30 to 17h00

Location:

Ghent
Bio-Accelerator
Technologiepark 21
9052 Ghent
 

Trainer:

Sven Degroeve

Registration start date:

25 April 2018 (10:00)

Registration end date:

29 May 2018 (10:00)