Generalized Deep Recurrent Learning for Object Recognition
Deep neural networks (DNNs) have revolutionized the use of artificial neural networks in complex applications such as computer vision, speech recognition, medical imaging, and bioinformatics. Deep learning essentially enables autonomous learning of multi-layered (deep) large scale neural networks using large scale data. The organization and workings of recurrent neural networks (RNNs) mimics the overall working principle of neural pathways observed in the biological vision system. This talk outlines the latest research in the Vision Lab at Old Dominion University on generalizing the DNNs by incorporating simultaneous recurrent connections for different types of recognition tasks.
Dr. Khan M. Iftekharuddin is a professor in the department of electrical and computer engineering and an Associate Dean for Research in the Batten College of Engineering at Old Dominion University (ODU). He serves as the director of ODU Vision Lab. He is also a member of biomedical engineering program at ODU. Much of his research had focused on different aspects of computer vision, machine learning and signal/image processing problems. He serves as a Senior Associate Editor for Optical Engineering journal and as an Associate Editor for multiple journals including IEEE Transaction in Image Processing, IEEE Transaction in Neural Networks and Learning Systems, Cognitive Systems Research, and Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization. He is a Fellow of SPIE, a Senior Member of IEEE, INNS and OSA.