ELM Lecture: Extreme Learning Machine: Towards Tuning-Free Learning
Date: 26 Jun 2012 - 26 Jun 2012
Venue: SIMTech Auditorium, Tower Block, Level 3
Neural networks (NN) and support vector machines (SVM) play a fundamental key roles in machine learning and data analysis. However, it is known that these popular learning techniques face some challenging issues such as: intensive human intervene, slow learning speed, poor learning scalability. This talk will introduce a new learning technique referred to as Extreme Learning Machine (ELM). ELM is capable of learning up to tens of thousands faster than NN and SVMs, providing unified implementation for regression, binary and multi-class applications. ELM can produce not only good results for sparse datasets but also efficient for large size of applications. From both theoretical and practical points of view, NN and SVM/LS-SVM only produce suboptimal solutions for ELM. ELM is efficient to time series, online sequential, incremental applications. This lecture will discuss its potential applications in complex systems, business intelligence, event predictions, etc.
2.00pm Presentation by Associate Professor Huang Guang-Bin
3.00pmQ & A
3.20pm Refreshment & Networking
About the Speaker
Huang Guang-Bin received the BSc degree in applied mathematics and M.Eng degree in computer engineering from Northeastern University, P. R. China, in 1991 and 1994, respectively, and Ph.D degree in electrical engineering from Nanyang Technological University, Singapore in 1999. During undergraduate period, he also concurrently studied in Applied Mathematics department and Wireless Communication department of Northeastern University, P. R. China. From June 1998 to May 2001, he was employed as a Research Fellow at the Singapore Institute of Manufacturing Technology (formerly known as Gintic Institute of Manufacturing Technology) where he led and implemented several key industrial projects (viz. Chief architect/designer and technical leader of Singapore Changi Airport Cargo Terminal Upgrading Project, etc). From May 2001, he has been working as an Assistant Professor and subsequently as an Associate Professor (with tenure) at the School of Electrical and Electronic Engineering, Nanyang Technological University. His current research interests include machine learning, computational intelligence, extreme learning machine, pattern recognition, games, and remanufacturing. He has published 15 full-length papers in IEEE Transactions and received 1400 SCI citations over his work. He was Program Chair of IEEE TENCON2009 (IEEE Region 10 flagship conference with 550+ registered participants). He serves as an Associate Editor of Neurocomputing and IEEE Transactions on Systems, Man and Cybernetics - Part B. He is a senior member of IEEE.
Registration for the seminar is free of charge. Seats are available on a first-come, first-served basis. To reserve a place, please register online.
For technical enquiries, please contact Ms Yan Wen Jing, Planning and Operations Management Group, Email: firstname.lastname@example.org, Tel: 67938972
For general enquiries, please contact Ms Alice Koh, Email: email@example.com