乐于分享
好东西不私藏

8月1日“软件新技术讲坛” 学术报告 - Prof. Ponnuthurai Nagaratnam Suganthan

8月1日“软件新技术讲坛” 学术报告 - Prof. Ponnuthurai Nagaratnam Suganthan

Deep Neural Networks Trained by Closed-form/BP with Multiple Output Layers/Heads

时间:2026年8月1日(星期六)14:15

地点:人工智能学院 C215室

Prof. Ponnuthurai Nagaratnam Suganthan

College of Engineering
Qatar University

摘  要

This talk will first introduce the main randomization-based feedforward learning paradigms with closed-form solutions. Several instantiations of the randomized feedforward neural networks will be presented, including the random vector functional link network. The randomized neural networks can be trained using closed-form solution (CFS). We will also present deep random vector functional link implementations with multiple output heads. This structure with multiple output heads can also be trained by backpropagation (BP) and also in a hybrid manner using BP and CFS. Hyperparameter tuning will be addressed in detail. The talk will also present extensive benchmarking studies using image/tabular classification and forecasting datasets.

报告人简介

Ponnuthurai Nagaratnam Suganthan received the B.A degree and M.A degree in Electrical and Information Engineering from the University of Cambridge, UK in 1990, and 1994, respectively. He received an honorary doctorate (i.e. Doctor Honoris Causa) in 2020 from University of Maribor, Slovenia. After completing his PhD research in 1995, he served as a pre-doctoral Research Assistant in the Dept. of Electrical Engineering, University of Sydney in 1995–96 and a lecturer in the Dept. of Computer Science and Electrical Engineering, University of Queensland in 1996–99. Since August 2022, he has been with the College of Engineering, Qatar University, as a professor.
His research interests include randomization-based learning methods, swarm and evolutionary algorithms, pattern recognition, deep learning and applications of swarm, evolutionary & machine learning algorithms. He was selected as one of the highly cited researchers by Thomson Reuters Science Citation yearly from 2015 to 2023 in computer science. He served as the General Chair of the IEEE SSCI 2013. He has been a member of the IEEE (S'91, M'92, SM'00, Fellow 2015) since 1991 and an elected AdCom member of the IEEE Computational Intelligence Society (CIS) in 2014-2016. He was an IEEE CIS distinguished lecturer (DLP) in 2018-2021. He is a founding co-editor-in-chief of Swarm and Evolutionary Computation (2010 - 2023).
欢迎参加