Seminario: Deep learning, neural networks and kernel machines: towards a unifying framework
Día: Lunes 23 de noviembre de 2020
Hora: 11:00 horas
Modalidad: Seminiario ONLINE
Ponente: Johan Suykens. KU Leuven, ESAT-Stadius and Leuven.AI Institute
Over the last decades, with neural networks and deep learning, several powerful architectures have been proposed, including e.g. convolutional neural networks (CNN), stacked autoencoders, deep Boltzmann machines (DBM), deep generative models and generative adversarial networks (GAN). On the other hand, with support vector machines (SVM) and kernel machines, solid foundations in learning theory and optimization have been achieved. Could one combine the best of both worlds?
Within this talk, we outline a unifying picture and show several new synergies, for which model representations and duality principles play an important role. A recent example is restricted kernel machines (RKM), which connects least squares support vector machines (LS-SVM) to restricted Boltzmann machines (RBM). New developments on this will be shown for deep learning, generative models, multi-view and tensor based models, latent space exploration, robustness and explainability.
Bio: Johan Suykens is is a full Professor with KU Leuven, where he serves as program director of Master AI. He received the master degree in Electro-Mechanical Engineering and the PhD degree in Applied Sciences from the Katholieke Universiteit Leuven, in 1989 and 1995, respectively. He has been a Postdoctoral Researcher at the University of California, Berkeley, and also with the Fund for Scientific Research FWO Flanders. He has authored and edited 6 books, and he is the author of more than 700 publications. He has also organized and chaired several international workshops and conferences. He has been granted 2 ERC Advanced Grant in 2011 and 2017, and he has been elevated IEEE Fellow 2015 for developing the least squares support vector machines.