Your browser version is outdated. We recommend that you update your browser to the latest version.

PREMIA Short course 2018


The Singapore Pattern Recognition and Machine Intelligence Association (PREMIA) is pleased to organise a short course this year:

Date: 21-23 May 2018

Time: 9.00 am --- 5.00pm

Venue: Seminar Room 7 at School of Computing, COM1, level 2, 13 Computing Drive; Singapore 117417

Kent Ridge Campus, National University of Singapore


This short course will cover several topics, running back-to-back over consecutive days on the topics shown below.  Participants should choose at least TWO TOPICS. This permits greater flexibility for participants, especially those from industry, to tailor the course to suit their needs.


 Schedule (21 – 23 May 2018):








21 May AM

9:00 – 12:30

Dr. CHAN Kap Luk

Yau Lee Holdings Ltd

Image Processing Fundamentals and Applications with Hands-on


21 May 2018

13:30 – 17:00

Dr. LEE Gim Hee

National University of Singapore

3D Vision for Self-driving Cars and Autonomous Drones


22 May 2018

9:00 – 12:30

13:30 - 17:00

Dr. LEE Hwee Kuan

Bioinformatics Institute

Deep Learning Theory and Practice


23 May 2018

9:00 – 12:30


Bioinformatics Institute

Machine Learning Fundamentals


23 May 2018


Dr. Sinno Jialin Pan

Nanyang Technological University

Transfer Learning: Fundamentals and applications


Deadline for registration: April 20, 2018  April 15, 2018; 


Course Fees:


TWO Topics

THREE Topics

FOUR Topics

FIVE Topics

Members of PREMIA





Non-PREMIA members





Student members of PREMIA*





Student non-PREMIA members*





 (* Limited seats only)

The above registration fees include instructional materials, light refreshments, and one year free PREMIA membership renewal for existing members and one year free membership for non-PREMIA members.



To register, please email to PREMIA course coordinator (given below) with your choices of courses, name, email address, contact telephone number, and make payment to PREMIA in one of the following two modes:

  1. By internet banking funds transfer: please transfer to PREMIA bank account shown below:

Bank name: Standard Chartered Bank - Holland Village Branch

Branch code: 024

Account name: Pattern Recognition & Machine Intelligence Association

Account no.: 24-0-831177-7


This is the preferable payment mode. Please inform PREMIA’s Treasurer Dr. CHENG Li (e-mail: with the screenshot of the online transfer after you have performed the bank transfer.

  1. By cheque: please cross your cheque, make it payable to 'PREMIA', write the name and contact number of each registrant on the back of your cheque, and send it to:


c/o: Dr. CHENG Li

Bioinformatics Institute,

30 Biopolis Street, #07-01 Matrix Building,

Singapore 138671


Please contact PREMIA’s Treasurer Dr. CHENG Li (e-mail: before you make any payment and inform him with the carbon copy/photo of the check once you mail the check out.


PREMIA course coordinator:

Dr. Xiong Wei, Email:

Dr. Zhou Jiayin, Email:


Important notice:  The course program and its details provided here as they are without any guarantee. PREMIA reserves the rights to change, postpone or cancel the entire program or parts of it as it deems necessary. Please check with course coordinators for the latest course information. 


Course lecturers and topic abstracts



Lecture Title: Image Processing Fundamentals and Applications with Hands-on

Instructor: Dr CHAN Kap Luk 


This short course covers the following fundamental topics in image processing, serving the needs for both image visualization and computerized image analysis: image formation, imaging principles, and image enhancement, color image processing, morphological and nonlinear image processing, multi-resolution image processing. The course is based on the chapters from two digital image processing textbooks: Digital Image Processing by Gonzalez and Woods and Digital Image Processing by William Pratt. The course will emphasize on the image processing operations and their applications instead of focusing on theoretical aspects of the operations. Demonstration of some of the image processing operations will be done using Octave (Matlab like Open Source Platform) or python with Open CV.  This course is suitable for beginners who need to apply image processing to solve real world problems. Participants are advised to bring a laptop to try out examples and exercises.


Bio of Instructor:

Dr Kap Luk CHAN obtained his PhD degree in Robot Vision from Imperial College of Science, Technology and Medicine, University of London, London, U.K. in 1991. He was an associate professor in the School of Electrical and Electronic Engineering, Nanyang Technological University (NTU) and had spent for more than 20 years in academic research. His research areas include Image Analysis and Computer Vision, Image and Video Retrieval, Image Semantics and Understanding, Biomedical Signal/Image Analysis for Computer Assisted Clinical Diagnosis.  He has published more than 140 papers in international conferences and journals, and in edited books. He has also served as a consultant in local companies. He is now the Director of AI Centre of Yau Lee Holdings Limited in Hong Kong. He is a member of IEEE, IET and PREMIA.



Lecture Title: Deep Learning: Fundamentals and Applications

Instructor: Dr LEE Hwee Kuan


Deep learning has become revolutionary techniques in many research areas of artificial intelligence in recent years. This course will cover the practice of deep learning methods and basic theory in deep learning techniques. The first half-day will cover the basic theory for deep learning covering introduction to neural networks, backpropagation based optimization techniques, how to train a neural network for the specific task, the convolutional neural networks, recurrent neural networks, and their applications for image classification, object detection, and image segmentation. The second half day will give hands-on introduction on deep learning methods implementation. Practices, including how to design a deep neural network for a specific application, how to build and implement the network with the open-source TensorFlow platform, etc. By taking the course, the audience will gain basic knowledge about deep learning and can learn to design and train a neural network for specific tasks.

Pre-requirements: You need to bring along your laptop. Before the course, please ensure the following:

  1. Install the DL framework by themselves before the course. They can follow this link:
  2. Download MNIST dataset (four .gz files) from
  3. Clone or download Tensorflow source code from



Bio of Instructor:

Dr. LEE Hwee Kuan is currently a Senior Principal Investigator of the Imaging Informatics division in Bioinformatics Institute. His current research work involves developing of computer vision aglorithms for clinical and biological studies. Hwee Kuan obtained his Ph.D. in 2001 in Theoretical Physics from Carnegie Mellon University with a thesis on liquid-liquid phase transitions and quasicrystals. He then held a joint postdoctoral position with Oak Ridge National Laboratory (USA) and University of Georgia where he worked on developing advanced Monte Carlo methods and nano-magnetism. In 2003, with an award from the Japan Society for Promotion of Science, Hwee Kuan moved to Tokyo Metropolitan University where he developed solutions to extremely long time scaled problems and a reweighting method for nonequilibrium systems. In 2005 he returned home to join Data Storage Institute, investigating novel recording methods such as hard disk recording via magnetic resonance. In 2006, he joined Bioinformatics Institute as a Principle Investigator in the Imaging Informatics Division. URL:



Lecture Title: Machine Learning: Fundamentals and Applications

Instructor: Dr. CHENG Li


This lecture deals with the fundamentals of learning machines under uncertainty. We start by showing a set of working examples of real-world ground-breaking machine learning systems. This is followed by a more in-depth introduction to statistical graphical models, which enable us to discuss concretely the three main machine learning components, namely representation, inference, and learning (aka parameter estimation). Related books includes "Pattern Recognition and Machine Learning" by Chris Bishop, "Pattern Classification and Scene Analysis" by Duda and Hart, and "Probabilistic Graphical Models: Principles and Techniques" by Koller and Friedman.


Bio of Instructor:

Dr. CHENG Li is a principal investigator in Bioinformatics Institute (BII). His research expertise is mainly on computer vision and machine learning. His research work has resulted in over 60 referred papers including those published at journals such as IEEE Trans. Pattern Analysis and Machine Intelligence, International Journal of Computer Vision, as well as conferences such as ICML, NIPS, ICCV, CVPR, MICCAI. Together with Matti Pietikainen and colleagues, He co-edited two books (one published 2011 by Springer, and one at 2009 by IGI Global), and co-organized two international workshops on motion analysis and computer vision. Together with Alex Smola and Marcus Hutter, He co-organized an international summer school on machine learning at Australia. He is a senior member of IEEE. He also holds an adjunct assistant professorship in the School of Computing, National University of Singapore (NUS). URL:




Lecture Title: 3D Vision for self-driving cars and autonomous drones

Instructor: Dr. LEE Gim Hee


The abilities to build a 3D map of the environment and do pose estimation respect to this map is of utmost importance for robots such as self-driving cars and autonomous drones to achieve full autonomy. Cameras are a good choice as the main sensor for the mapping and pose estimation tasks because they are low-cost, light-weighted, and the images taken from the cameras are information-rich. In this course, I will first talk about some of the popular cameras/camera configurations for robotics, e.g. monocular, stereo, multi- and RGB-D cameras.  Next, I will discuss the details of some of the 3D vision algorithms, e.g. camera modeling, camera calibration, epipolar geometry, RANSAC, minimal problems, and Structure-from-Motion/Visual SLAM, that are essential for the mapping and pose estimation tasks. Finally, I will show the results from some of my previous works on vision-based self-driving car and autonomous drone. 


Bio of Instructor:


Dr LEE Gim Hee currently is an Assistant Professor at the Department of Computer ScienceNational University of Singapore (NUS). He was a researcher at Mitsubishi Electric Research Laboratories (MERL), USA from June 2014 to July 2015. Prior to MERL, he did his PhD in Computer Science at ETH Zurich from January 2009 to March 2014 under the supervision of Prof. Marc Pollefeys. He received his B.Eng with first class honors and M.Eng degrees from the Department of Mechanical Engineering, NUS in June 2005 and February 2008 respectively. He worked at DSO National Laboratories in Singapore as a Member of Technical Staff from August 2007 to December 2008. URL:




Lecture Title: Transfer Learning: Fundamentals and Applications

Instructor: Dr PAN Jialin, Sinno


Transfer learning is a learning paradigm motivated by human’s learning ability on transferring experience across different tasks or problems. Different from traditional machine learning paradigms, which assume training data and test data follow the same distribution, in transfer learning, training data and test data are usually drawn from different distributions or even represented in different feature spaces as they come from different domains or tasks. In this course, I will first give an overview on transfer learning. Prerequisites for attending the course: Basic mathematics background, e.g., linear algebra, probability.


Bio of Instructor:

Dr Sinno Jialin Pan is a Nanyang Assistant Professor at the School of Computer Science and Engineering at Nanyang Technological University (NTU), Singapore. Prior to joining NTU, He was a scientist and Lab Head of text analytics with the Data Analytics Department, Institute for Infocomm Research, Singapore. He received his Ph.D. degree in computer science from the Hong Kong University of Science and Technology (HKUST) in 2010. His research interests include transfer learning, and its applications to wireless-sensor-based data mining, text mining, sentiment analysis, and software engineering. More details are here: