报告主题：
An Optimisation Perspective on Neural Architecture Search
报告时间：
6月21日 10：00-11：00
报告地点：
人工智能与计算机学院B310会议室
报告摘要：
Machine Learning (ML) is a subset of Artificial Intelligence (AI) dedicated to constructing data-driven parametric predictive models. This presentation highlights the critical role of optimisation in ML, encompassing various phases of the modelling process. It explores three essential ML tasks: 1) selecting model variables through feature selection; 2) determining model parameters via model training; and 3) designing model structures, particularly through neural architecture search. All these tasks can be interpreted as aspects of neural model design, where the primary objective is to achieve the highest accuracy in ML model predictions. The speaker will present recent research addressing each of these challenges, offering insights into advanced optimisation techniques within the context of ML.
主讲人：
Ferrante Neri received his Laurea and Ph.D. degrees in Electrical Engineering from the Politecnico di Bari, Italy, in 2002 and 2007, respectively. He also obtained 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. Between 2009 and 2014, he was an Academy Research Fellow with the Academy of Finland, leading the project on Algorithmic Design Issues in Memetic Computing. He served at De Montfort University, Leicester, UK, from 2012 to 2019 and at the University of Nottingham, UK, from 2019 to 2022. Since 2022, he has been a Full Professor of Machine Learning and Artificial Intelligence at the University of Surrey, Guildford, and the Head of the Nature Inspired Computing and Engineering (NICE) Research Group. Additionally, he holds the title of Jiangsu Distinguished Professor at Nanjing University of Information Science and Technology. His research focuses on metaheuristic optimisation with applications in machine learning.
当前位置:
