Alexios Balatsoukas Stimming
Crash-course in Neural Network Compression
by Dr. Alexios Balatsoukas Stimming
Assistant Professor, Eindhoven University of Technology, Netherlands
When and Where
7th - 9th July 2025, 10:00 - 13:00
University Campus, exact location to be announced
Registration
Please register for the course at https://survey.tuc.gr/index.php/797724?lang=el
Registration deadline: 30 June
Abstract
This crash-course on neural network compression provides a comprehensive overview of essential techniques for optimizing deep learning models. We will begin with a short introduction to the operation and training of (convolutional) neural networks. We will then delve into neural network quantization, explaining how reducing the precision of weights and activations can decrease model size and computational requirements. We will also explore pruning, highlighting methods for removing redundant neurons and connections to streamline the network without significantly impacting task performance. Finally, we will introduce the concept of knowledge distillation, demonstrating how knowledge can be transferred from a large, complex model (teacher) to a smaller, simpler model (student) to achieve comparable performance with reduced computational resources. All topics will be accompanied by short in-class programming assignments. This crash-course equips participants with the knowledge and hands-on experience to effectively compress neural networks, making them more suitable for deployment in resource-constrained embedded devices.
Language: English
About the Speaker
Alexios Balatsoukas-Stimming (Senior Member, IEEE) received the Diploma and M.Sc. degrees in electronics and computer engineering from the Technical University of Crete, Chania, Greece, in 2010 and 2012, respectively, and the Ph.D. degree in computer and communications sciences from the École Polytechnique Fédérale de Lausanne (EPFL), Switzerland, in 2016. He was a Marie Skłodowska-Curie Post-Doctoral Fellow with European Laboratory for Particle Physics, Meyrin, Switzerland, for one year. He was a Post-Doctoral Researcher with the Telecommunications Circuits Laboratory, EPFL, from 2018 to 2019. He has been a Visiting Post-Doctoral Researcher with Cornell University, Ithaca, NY, USA, and the University of California at Irvine, Irvine, CA, USA. He is currently an Assistant Professor with the Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands. His research and teaching interests include VLSI circuits for communications, error correction coding theory and practice, and the applications of approximate computing and machine learning to signal processing for communications.
