Machine & Deep Learning - Practical introduction​


Practical introduction to Machine Learning & Deep Learning 

This 5 days course aims to provide basic understanding of the most used machine learning and deep learning algorithms. It is an intensive course that, without going into too much mathematical details, provides the necessary foundations to start testing, working with and evaluating those algorithms. Knowing how to manipulate these algorithms and their potential forms an important building block in the digital literacy required to prepare and live in Society 4.0 (see UNINEWS - Society 4.0).

The topics covered are: regression (linear, logistic), classification (K-NN), dimensionality reduction (PCA), support vector machines, clustering (K-means), decision trees, Bayesian learning, neural networks, deep neural networks (CNN, RNN and LSTM), data cleaning, models’ evaluation and features selection.


Target audience

By the end of the course, participants should be able to:

  • Categorize the different algorithms and their use cases
  • Efficiently select algorithms’ features and evaluate algorithms’ performance
  • Explain and use linear and logistic regression methods
  • Explain and use classification and clustering algorithms
  • Explain and use dimensionality reduction, decision trees and Bayesian learning
  • Explain and use artificial neural networks and deep learning methods 

This course would benefit:

  • Big data and business intelligence technicians
  • Business analysts
  • Big data and business intelligence project managers
  • Students from universities and schools of applied sciences at master level or higher

​The course is nevertheless open to other profiles of professionals and academics interested in discovering machine learning and deep learning and how they can be applied in their domain. 

Admission conditions

Given the density of the course no introduction to programming nor to mathematics can be provided. Participants are expected to bring their personal computers during the course with full administrative rights, be familiar with the basic use of R and Python and have basic familiarity with linear algebra and statistics.

Specific details on the requirements can be found in the additional documents.

A two hours R and Python course can be provided on Friday afternoon before the beginning of the course on Monday. Mention your interest to follow this course while registering. 


Upon successful completion of the course, the participants will be awarded with a Certificate of Completion issued by the Faculty of Economics and Business of the University of Neuchâtel.   



Deadline for application


CHF 1000.- / participant
including lunch and coffee breaks 

A limited number of scholarships are available for the students of the University of Neuchâtel. Contact us for an eligibility check before registration. 


University of Neuchâtel​
Faculty of Economics and Business
Avenue du 1er-Mars 26
CH-2000 Neuchâtel

Administrative Coordinator
Eliane Maalouf​
PhD candidate – Teaching Assistant    
Information Management Institute
Tél. 032 718 13 29  


Deadline for application

​All participation slots are now filled and registration to this course are closed.

Contact the course coordinator to be added to the waiting list and get informed about last minute places’ availabilities.



uk.png English


Administrative Coordinator
Eliane Maalouf​
PhD candidate -Teaching Assistant    
Information Management Institute
Tél. 032 718 13 29  

Academic direction

Prof. Paul Cotofrei
Associate Professor    
Information Management Institute     
University of Neuchâtel             
Tél. 032 718 13 78


Jacques Savoy, PhD, Prof.
Tél. 032 718 13 75

Marcus Liwicki, PhD, Prof.
Tél. 026 300 93 50

Eliane Maalouf
Tél. 032 718 13 29  


University of Neuchâtel​
Faculty of Economics and Business
Avenue du 1er-Mars 26
CH-2000 Neuchâtel