Aapo Hyvärinen, University of Helsinki and University College London

Aapo Hyvärinen

Neural networks: Artificial Intelligence or Genuine Statistics?

Abstract

Neural networks have, in the last few years, had enormous success as building blocks of artificial intelligence systems. In fact, they are increasingly considered the best way of building intelligence in domains such as machine vision, machine translation, or search engines. Here, I review the history and current understanding of how to build artificial intelligence, and why neural networks have been particularly successful. I will emphasize the importance of learning for intelligence, and how learning is related to statistical modelling.

Bio

Aapo Hyvarinen studied undergraduate mathematics at the universities of Helsinki (Finland), Vienna (Austria), and Paris (France), and obtained a Ph.D. degree in Information Science at the Helsinki University of Technology in 1997. After post-doctoral work at the Helsinki University of Technology, he moved to the University of Helsinki in 2003. In 2008, he was appointed Professor of Computational Data Analysis, and in 2013, Professor of Computer Science. In 2016, he became Professor of Machine Learning at the Gatsby Computational Neuroscience Unit, University College London, UK.

Aapo Hyvarinen is the main author of the books "Independent Component Analysis" (2001) and "Natural Image Statistics" (2009), and author or coauthor of more than 200 scientific articles. He is Action Editor at the Journal of Machine Learning Research and Neural Computation and Editorial Board Member in Foundations and Trends in Machine Learning. He has served as Contributing Faculty Member of Faculty of 1000 Prime. He is a classified as a Highly Cited Researcher by ISI Thomson Reuters, and Google Scholar gives him with more than 40,000 citations. His current work concentrates on applications of unsupervised machine learning methods to neuroscience.

Photograph: Veikko Somerpuro