2022-10-18, 10:30–11:15, Room 1
Several breakthroughs in artificial intelligence in recent years have been established through deep learning technologies, such as convolutional neural networks, variational autoencoders, generative adversarial networks, transformers and others. Neural networks and deep learning are flexible and powerful architectures. On the other hand with kernel machines solid foundations in learning theory and optimization have been achieved. In this talk we outline a unifying picture and show new synergies between neural networks, deep learning and kernel machines. New developments on this will be discussed for deep learning, generative models, multi-view and tensor based models, latent space exploration, robustness and explainability.
Johan A.K. Suykens is a full professor at KU Leuven. He is an IEEE Fellow and ELLIS Fellow. He has been awarded an ERC Advanced Grant 2011 and 2017. He is currently serving as associate editor for the IEEE Transactions on Neural Networks and Learning Systems and the IEEE Transactions on Artificial Intelligence. He is author and editor of several books in the areas of neural networks, support vector machines, kernel methods, and learning theory. He is currently program director of Master AI at KU Leuven.