This talk will cover a brief overview some of my PhD work, including Training CNNs with Low-rank Filters (ICLR 2016), and Deep Roots – training CNNs with sparse inter-filter connectivity (CVPR 2017). They would relate these contributions to their usage in the current state of the art networks for the Imagenet Large-Scale Visual Recognition Challenge (ILSVRC), including GoogLeNet (Inception) and ResNet.
Yani A. Ioannou is a Microsoft Research Ph.D. Scholar in the Department of Engineering at the University of Cambridge, and a graduate member of Jesus College. He is supervised by Professor Roberto Cipolla, head of the Computer Vision and Robotics group in the Machine Intelligence Lab, and Dr. Antonio Criminisi, a principal researcher at Microsoft Research. He is currently interested in methods of training convolutional neural networks (CNNs), and their application to problems in computer vision. He has in the past worked on 3D computer vision, and methods for processing and recognizing objects in large point clouds. In his spare time he’s worked on open source projects such as the Linux kernel and the Point Cloud Library (PCL).