Prof. Bart Romeny's Lecture: Brain-Inspired Computing - Neuro-Mathematics of Deep Learning
Title: Brain-Inspired Computing - Neuro-Mathematics of Deep Learning
Speaker: Prof. Bart M. ter Haar Romeny, TU/e, the Netherlands
Chair: Prof. Tianzi Jiang, Brainnetome Center, CASIA
Time: 14:30-16:30 Dec. 15, 2016
Venue: The Lecture Hall, 3rd floor of the Intelligence Building
[Abstract]
Deep Learning is a new disruptive technology that makes spectacular progress in image recognition and computer-aided diagnosis. The paradigm is based on the processing in a visual cascade of steps, much like in our visual system. A whole new field is emerging: brain-inspired computing.
There are many neuro-computational approaches to modeling the early stages of vision. The visual system stands out as one of the most intriguing 'last frontiers'. We have only just begun understanding it. Much progress has been made with modern optical imaging methods, opto-genetics, and advanced MRI methods. The lectures will discuss the physiology, geometry and the mathematics of early vision, where the concepts of multi-scale, multi-orientation, and multi-spatial frequency processing of images will take a natural role.
We will discuss how learning / self-organization of early stage filters is done, invariant feature detection, adaptive feedback for edge-preserving smoothing, color invariants, and contextual multi-orientation analysis, mimicked from the cortical columns with their characteristic pinwheel structure. Applications are discussed for medical imaging.
[Biography]
Prof. Bart M. ter Haar Romeny, PhD
Northeastern University, Sino-Dutch Biomedical and Information Engineering School, Shenyang, China, romeny@bmie.neu.edu.cn
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. His research interests focus on:
• fundamental brain-inspired computer vision research;
• multi-modal and interactive 3D visualization, with special attention to diffusion tensor imaging;
• computer-aided detection, in particular by diabetes screening from retina fundus images.
• image guided surgery, directed towards neurosurgery
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. 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 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.