When the state of the art is ahead of the state of understanding : unintuitive properties of deep neural networks

Loading...
Thumbnail Image
Publication date
2019
Reading date
Journal Title
Journal ISSN
Volume Title
Publisher
Metrics
Export
Abstract
Deep learning is an undeniably hot topic, not only within both academia and industry, but also among society and the media. The reasons for the advent of its popularity are manifold: unprecedented availability of data and computing power, some innovative methodologies, minor but significant technical tricks, etc. However, interestingly, the current success and practice of deep learning seems to be uncorrelated with its theoretical, more formal understanding. And with that, deep learning?s state-of-the-art presents a number of unintuitive properties or situations. In this note, I highlight some of these unintuitive properties, trying to show relevant recent work, and expose the need to get insight into them, either by formal or more empirical means.
Description
Keywords
Bibliographic reference
Serrà, Joan. When the state of the art is ahead of the state of understanding : unintuitive properties of deep neural networks. En: Mètode Science Studies Journal: Annual Review, 9 2019: 126-133