Seminar: Optimisation as the Code of Machine Learning: From Features to Architectures

Abstract  
 
Machine Learning (ML), a branch of Artificial Intelligence (AI), is centered around developing data-driven parametric predictive models. This presentation highlights the critical role of optimization across various stages of the ML modeling process. It focuses on three core tasks: (1) feature selection for identifying relevant model variables; (2) training to optimize model parameters; and (3) designing model architectures, with a particular focus on neural architecture search. Together, these tasks form essential components of neural model design, all directed toward enhancing predictive accuracy. The talk will explore recent advancements in addressing these challenges, offering insights into state-of-the-art optimization techniques and their applications in ML.
 
Speaker  
Ferrante Neri earned his Laurea and Ph.D. degrees in Electrical Engineering from the Politecnico di Bari, Italy, in 2002 and 2007, respectively. He further pursued advanced studies, obtaining a second Ph.D. in Scientific Computing and Optimization and a D.Sc. in Computational Intelligence from the University of Jyväskylä, Finland, in 2007 and 2010, respectively.
 
From 2009 to 2014, he was an Academy Research Fellow with the Academy of Finland, leading a pioneering project on Algorithmic Design Issues in Memetic Computing. He subsequently held academic positions at De Montfort University, Leicester, UK (2012–2019), and the University of Nottingham, UK (2019–2022).
 
Since 2022, Professor Neri has been a Full Professor of Machine Learning and Artificial Intelligence at the University of Surrey, Guildford. Formerly the Head of the Nature-Inspired Computing and Engineering (NICE) Research Group, he currently serves as the Associate Dean (International) for the Faculty of Engineering and Physical Sciences. Additionally, he is a Jiangsu Distinguished Professor at Nanjing University of Information Science and Technology.
 
Professor Neri’s research centres on metaheuristic optimisation and its transformative applications in machine learning, reflecting his commitment to advancing innovation in computational intelligence.