Back to ListLecture by Prof. Cees Snoek online
Progress in artificial intelligence has been astonishing in the past decade. Cars self-driving on highways, machines beating go-masters, and cameras categorizing images in a pixel-precise fashion are now common place, thanks to data-and-label supervised deep learning. Despite the impressive advances, it is becoming increasingly clear that deep learning networks are heavily biased towards their training conditions and become brittle when deployed under real-world situations that differ from those perceived during learning in terms of data, labels and objectives. Simply scaling-up along all dimensions at training time seems a dead end, not only because of the compute, storage and ethical expenses, but especially as humans are easily able to generalize robustly in a data-efficient fashion. Several learning paradigms have been proposed to account for the limitations of deep learning with the i.i.d. assumption. Shifting data distributions are attacked by domain adaptation and domain generalization, changing label vocabularies are the topic of interest in zero-shot, open set and open world learning, while varying objectives are covered in meta-learning and continual learning regimes. However, there is as of yet no learning methodology that can dynamically learn to generalize and adapt across domains, labels and tasks simultaneously, and do so in a data-efficient fashion. This is the ambitious long-term goal of ‘real-world learning’ and some initial approaches and results towards its objective will be presented.
Cees Snoek is a full professor in computer science at the University of Amsterdam, where he heads the Video & Image Sense lab. He is also a director of three public-private AI-research labs: QUVA lab with Qualcomm, Atlas lab with TomTom and AIM lab with the Inception Institute of Artificial Intelligence. At University spin-off Kepler Vision Technologies he acts as Chief Scientific Officer. He is also co-founder of the Netherlands Innovation Center for Artificial Intelligence. He was previously visiting scientist at Carnegie Mellon University and UC Berkeley, head of R&D at University spin-off Euvision Technologies and managing principal engineer at Qualcomm Research Europe. His research interests focus on making sense of video and images. He has published over 250 refereed journal and conference papers in computer vision, multimedia analysis and machine learning and serves on the editorial board of IEEE Transactions on Pattern Analysis and Machine Intelligence. Cees is an Ellis Fellow, recipient of an NWO Veni career award, a Fulbright Junior Scholarship, an NWO Vidi career award, and the Netherlands Prize for ICT Research. Together with his Ph.D. students and Post-docs he has won several best paper awards.
