Target audience

This course is aimed at professionals and investigators from diverse areas who want to learn how to apply neural networks on diverse problems, or who want to learn about the possibilities, applicability, and variants of neural networks.

Description

Since their earliest conception in the 1940s, artificial neural networks have been alternatively regarded as extremely promising machine learning models, capable of learning anything, and as glorified linear combinations, unable to achieve relevant results in practice.

However, along the last decade, the availability of general-purpose GPU architectures and large quantities of data has enabled the rise of deep neural networks, which have attained state-of-the-art performance in many applications, from image classification to text translation. This has given rise to a whole new field of research, ranging from generative models to adversarial attacks (and defenses against them).

This course is intended as a first contact with artificial neural networks, followed by an overview of the different architectures that are currently available:

• Introduction to neurons and neural networks
• Training with backpropagation
• Challenges and solutions to train deep neural networks
• Convolutional networks
• Adversarial examples
• Generative models
  
  • Autoregressive models
  • Autoencoders
  • Variational autoencoders (VAE)
  • Generative adversarial networks (GAN)
• Transformers and BERT
• Recurrent neural networks

The practical sessions use the Python library TensorFlow to implement some of the models discussed in the course, with particular emphasis on how to adapt the networks to the characteristics of a specific problem.

Course prerequisites

Basic knowledge of the Python programming language is required (as for instance taught in Module 4 of this year's program).

Exam / Certificate

If you take part in all 5 sessions you will receive a certificate of attendance via e-mail after the course ends.

Additionally, you can take part in an exam. If you succeed in this test a certificate from Ghent University is issued.
The exam consists of a take home project assignment. You are required to write a report by a set deadline.

Type of course

This is an on campus course. We offer blended learning options if, exceptionally, you can't attend a class on campus.

Schedule

Five Thursday evenings in April and May 2023: April 20 and 27, May 4, 11 and 25, 2023, from 5.30 pm to 9 pm

Venue

UGent, Faculty of Science, Campus Sterre, Krijgslaan 281, Ghent. Building S9, 3rd floor, pc room 3.1 (Konrad Zuse).

Teacher

Dr. Daniel Peralta is a post-doctoral researcher at the Department of Applied Mathematics, Computer Science and Statistics of the Faculty of Sciences of Ghent University. He obtained his PhD at the University of Granada (Spain), tackling large-scale fingerprint identification.
His research has focused on machine learning, especially in large-scale scenarios, and has involved several collaborations with industry to apply such techniques on problems ranging from railway maintenance scheduling to compound activity prediction. Within his current position at the VIB, this research is applied on biological data. He currently teaches Big Data Science courses at Ghent University, in the Master of Statistical Data Analysis and the Master in Computer Science.

Course material

Acces to slides and code for the practical sessions

Fees

A different price applies, depending on your main type of employment.

*If two or more employees from the same company enrol simultaneously for this course a reduction of 20% on the module price is taken into account, starting from the second enrolment.

Register

Register for this course

UGent PhD students

As UGent PhD student you can incorporate this 'specialist course' in your Doctoral Training Program (DTP). To get a refund of the registration fee from your Doctoral School (DS) please follow these strict rules and take the necessary action in time. The deadline to open a dossier on the DS website (Application for Registration) for this course is March 20, 2023.

Opening a dossier with your DS does not mean that you are enrolled for the course with our academy. You still need to enrol via the registration form on this site.

It is you or your department that pays the fee first to our academy. The Doctoral School refunds that fee to you or your department once the course has ended.

It is not obligatory to participate or succeed in the exam.