We are proud to announce that as part of the France-Brazilian Chairs in São Paulo State / 2016, Prof. Matthieu Cord from Pierre et Marie Curie University / Paris will offer us two seminars on cutting-edge themes related to Deep Learning, the newest development of Machine Learning.
Both talks will happen at FEEC’s Congregation Room (pointer C). Free admittance up to the room’s capacity.
Prof. Matthieu Cord will also offer a short course on Deep Learning for visual tasks on early August, to be announced soon — stay tuned!
Friday 24 June, 17h00
Deep learning challenges for Visual AI
In recent years we have witnessed an explosion of successful applications of deep learning, including speech recognition, automatic translation, self-driving cars, recommender systems, and computers that can beat professional Go players. Deep networks designed for those tasks have up to billions of parameters, which take a huge amount of resources — data, memory and computing power — to train.
I will overview deep learning methodology for visual understanding, commenting on their historical development, and then detailing their architectures, and the tricks needed for learning. I will then discuss recent key issues, and applications on image segmentation or video prediction.
Friday 1st July, 17h00
Deep learning and weak supervision for image classification
Deep learning and Convolutional Neural Networks (CNN) are state of the art for many visual recognition tasks, e.g. image classification, or object detection. To better identify or localize objects, bounding box annotations are often used. Those rich annotations are costly to get, motivating the development of Weakly Supervised Learning (WSL) models.
We discuss several strategies to automatically select relevant image regions from weak annotations (e.g. image-level labels) in deep CNN. We also introduce our architecture WELDON for WEakly supervised Learning of Deep cOnvolutional neural Networks. Our deep learning framework, leveraging recent improvements on the Multiple Instance Learning paradigm, is validated on several recognition tasks.
Matthieu Cord is Full Professor at the Computer Science Department LIP6, at UPMC/Paris/France. In 2009, he was nominated at the IUF (French Research Institute) for a 5 years delegation position. He is currently CNRS scientific advisor for INS2I. His research interests include Computer Vision, Pattern Recognition and Machine Learning. He developed several interactive learning systems for content-based image and video retrieval. He is now focusing on Machine Learning for Multimedia processing, Deep Learning for visual data recognition, and Computational cooking. M. Cord has published a hundred scientific publications, including several recently published on deep learning (NIPS, ECCV, ICCV, CVPR). He is involved in several French (ANR, CNRS) and international projects (European IP and NoE, Singapore, Brazil, Canada) on those topics.