|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
Generalizing Convolutions for Deep Learning
If you have a question about this talk, please contact lecturescam.
Please be aware that this event may be recorded. Microsoft will own the copyright of any recording and reserves the right to distribute it as required.
Arguably, most excitement about deep learning revolves around the performance of convolutional neural networks and their ability to automatically extract useful features from signals. In this talk I will present work from AMLAB where we generalize these convolutions. First we study convolutions on graphs and propose a simple new method to learn embeddings of graphs which are subsequently used for semi-supervised learning and link prediction. We discuss applications to recommender systems and knowledge graphs. Second we propose a new type of convolution on regular grids based on group transformations. This generalizes normal convolutions based on translations to larger groups including the rotation group. Both methods often result in significant improvements relative to the current state of the art.
Joint work with Thomas Kipf, Rianne van den Berg and Taco Cohen.
This talk is part of the Microsoft Research Cambridge, public talks series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsPathology Seminars Cambridge Finance EPOC talks
Other talksMorphologically Computing Soft Robots toward Self-Organizing Machines Spacetime near an extreme horizon Evaluating ex-situ conservation of threatened plants in the botanic garden network Financial Market History: Reflections on the Past for Investors Today TBC Norwegian Romani - the 'languageness' of a Para-Romani variety