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

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

DSpace Repository

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

Show full item record

View       (5.569Mb)

Exportar a Refworks
    
Serrà, Joan
This document is a artículo publicadoDate2019
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.

    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

This item appears in the following Collection(s)

Show full item record

Search DSpace

Advanced Search

Browse

Statistics