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

[Update on May 7, 2017] The short course will be held as originally scheduled 22-25 May, 2017. The lecture room is changed to E4-04-02, National University of Singapore, Kent Ridge Campus.


[Update on April 21, 2017]

PREMIA has received some urgent requests to attend the short course as scheduled May 22-25, 2017. Therefore, we will continue to observe - please do the registration but NOT payment for the course if you are interested to attend the course. We need to have at least some registrations to break even for the cost.  Please watch out this page for updates. 


[Update on April 20, 2017]

Important!!! Early in 2017, the course was scheduled during May 22-25, 2017. However, due to insufficient responses from the audience, this course will be postponed to a later date. We apologize for any inconvenience caused. If you have any suggestions on the possible dates and/or the contents of the course, please contact PREMIA. 


[Update on Mar 26, 2017]

PREMIA Short Course 2017


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

Date: 22 to 25 May 2017

Time: 9.00 am --- 5.00pm

Venue: Block E4-04-02, NUS Faculty of Engineering,

Kent Ridge Campus, NUS


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


Schedule (22-25 May 2017):






22 May
Full day

9:00 – 17:00

Dr. CHAN Kap Luk

Xjera Labs Pte Ltd

Image Processing Fundamentals and Applications with Hands-on

23 May Full day

9:00 – 17:00

Dr. Robby TAN

National University of Singapore

Computer Vision Fundamentals: 3D Reconstruction and Motion Analysis

24 May Morning

9:00 – 12:30

Dr. Li Cheng

Bioinformatics Institute

Machine Learning Fundamentals

24 May

13:30 – 17:00

Dr. Sinno Jialin Pan

Nanyang Technological University

Transfer Learning: Fundamentals and applications

25 May
Full day

9:00 – 17:00

Dr. Feng Jiashi

National University of Singapore

Deep Learning: Fundamentals and Advances



Day 1

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

Date & Time: 9:00 -17.00, 22 May 2017

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 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 with Octave version 4, Open CV 2.4 installed at least.


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 Managing Director of Tolendata Singapore R&D Centre Private Limited and a Director of Technology in Stratech Systems Limited. He is a member of IEEE, IET and PREMIA.



Day 2

Lecture Title: Computer Vision Fundamentals: 3D Reconstruction and Motion Analysis

Date & Time: 9:00 -17.00, 23 May 2017

Instructor: Dr Robby TAN 


There are four pillars of computer vision: recognition, 3D reconstruction, motion, and low level vision. This course focuses on two of them, namely, 3D reconstruction and motion analysis. There are many applications of these two pillars, ranging mixed reality, industrial automation, robotics to surveillance, self-driving cars, road traffic monitoring, etc.  In this short course, the topics in 3D reconstruction includes camera extrinsic and intrinsic properties, homography, epipolar geometry, fundamental matrix, depth from stereo, structure from motion, etc. Aside from these core topics of 3D vision, the discussion also covers Bayesian probabilistic modeling, graphical models (MRFs), and optimization techniques. For the motion analysis, the topics include optical flow, sequential data, Kalman and particle filters, and motion segmentation.


Bio of Instructor:

Robby Tan is an assistant professor at both Yale-NUS College and Department of Electrical and Computer Engineering, National University of Singapore (NUS). His main research is in computer vision and deep learning (machine learning), particularly in the domains of bad weather, physics-based and motion analysis. Before coming to Singapore, he was an assistant professor in Department  of Information and Computing Sciences, Utrecht University, the Netherlands. His previous affiliations include Imperial College London, and NICTA/the Australian National University, working with Prof. Richard Hartley. He received his PhD from the University of Tokyo, under the supervision of Prof. Katsushi Ikeuchi.



Day 3 (AM)

Lecture Title: Machine Learning: Fundamentals and Applications

Date & Time: 9:00 -12.30, 24 May 2017

Instructor: Dr. Li Cheng


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. Li Cheng 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).


Day 3 (PM)

Lecture Title: Transfer Learning: Fundamentals and Applications

Date & Time: 13.30-17:00, 24 May 2017

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:


Day 4

Lecture Title: Deep Learning: Fundamentals and Applications

Date & Time: 9:00am -17.00pm, 25 May 2017

Instructor: Dr FENG Jiashi


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 recent advances in deep learning techniques. The first 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 Caffe platform, how to tune the network with debugging, will be taught   step by step. The second half-day will cover recent advances, ranging from network architectures, optimization techniques to applications in computer visions. In particular, the course will cover 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, long short-term memory (LSTM) unit and their applications for image classification, object detection, image segmentation and image description generation. The course will present both basic knowledge about deep learning as well as the recent advances in this attractive area. 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.


Bio of Instructor:

Dr. Feng Jiashi is currently an assistant professor with the department of Electrical and Computer Engineering at National University of Singapore. He received PhD from NUS in 2014 under the supervision of Shuicheng Yan and Huan Xu, and BS degree from USTC. Before joining NUS, He was a postdoc researcher in the EECS department and ICSI at the University of California, Berkeley, working with Trevor Darrell. I also spent several wonderful months at Technion, Israel, as a visiting student in the group of Shie Mannor. More details are here:


Course Fees:


Any TWO days

Any THREE days

All FOUR days

Members of PREMIA








Student members of PREMIA*




Student non-members*




 (* Limited seats only)

The above registration fees include instructional materials, refreshments, and one year free membership renewal for members and one year free membership for non-members. Early registration will enjoy discounts.



To register, please register online at URL. Registration will be confirmed upon receipt of course fee, which can be paid by either cheque or Internet banking funds transfer.

For cheque payment, 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:

Pattern Recognition and Machine Intelligence Association (PREMIA)

Attn: Dr. CHENG Li

c/o: Bioinformatics Institute,

30 Biopolis Street, #07-01 Matrix Building,

Singapore 138671


For Internet banking funds transfer, the account detail is 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


Please inform PREMIA’s Treasurer Dr. CHENG Li (e-mail: after you have made the fund transfer.  For further details on payment, please also email Dr CHENG Li.

If you have further enquiries, please contact PREMIA short course coordinator:

Dr. Bappaditya Mandal, Email:


Important notice: The dates may change based on the availability of tutors and attendants. PREMIA's decision will be final.


Please fill in the PREMIA Short Course 2017 Registration Form



This website was last updated on Mar 25, 2017.