Your browser does not support JavaScript!
[演講訊息] 107/05/02(三) Special Topics in Deep Learning/ Prof. Bart ter Haar Romeny


Special Topics in Deep Learning 

Prof. Bart ter Haar Romeny, Eindhoven University of Technology, Netherlands


2nd  May 2018(Wed.) 13:30-16:00 pm

IB-501 , Taiwan Tech 


Deep learning is one of the fastest growing branches in machine learning, due to its spectacular performance in human cognitive tasks. Its main implement-tation is through ‘convolutional neural networks (CNNs). A typical CNN has many layers (is ‘deep’). In 2012 the challenge to classify the images of the ImageNet database with 14 million images was won with a strikingly better performance than earlier methods. The deep structure of many convolutional layers is also recognized in our human visual perception. CNNs find applications in scene recognition, self-driving cars, medical diagnosis, translations etc. The technology is feasible, as today we have abundant computing power, and access to big data. It is embraced by the biggest companies (Apple, Google, Facebook, Baidu), and is rapidly transforming many areas of our technological society. Prof. Romeny will provide more depth information of deep learning from the viewpoint of pooling layer, types of networks, ResNet, U-net, data augmentation in this lecture.



Bart ter Haar Romeny (1952) is professor in biomedical image analysis. He has experience in biologically-inspired computer vision research and computer-aided diagnosis applications for over 25 years. He received the MSc degree in applied physics from Delft University of Technology in 1978, PhD from Utrecht University in 1983 in biophysics. He closely collaborates with industries and (national and international) hospitals and research groups. Currently he is project leader of the Sino-Dutch RetinaCheck project, a large screening project for early detection of diabetic retinopathy in Liaoning, China.

He is an enthusiastic educator. He authored an interactive tutorial book on multi-scale computer vision techniques, written in Mathematica, edited a book on non-linear diffusion theory in computer vision and is involved in (resp. initiated) a number of international collaborations on these subjects. He is author/co-author of over 200 refereed journal and conference papers, 12 books and book chapters, and holds 2 patents. He supervised 29 PhD students, of which 4 graduated cum laude, and over 140 Master students. He is senior member of IEEE, associate member of the Chinese Brainnetome consortium, visiting professor at the Chinese Academy of Sciences in Beijing, member of the Governing Board of IAPR, Fellow of EAMBES, and chairman of the Dutch Society for Pattern Recognition and Image Processing.