NAGIOS: RODERIC FUNCIONANDO

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

Repositori DSpace/Manakin

dc.contributor.author	Serrà, Joan	es
dc.date.accessioned	2021-06-14T11:16:10Z
dc.date.available	2021-06-14T11:16:10Z
dc.date.issued	2019	es
dc.identifier.citation	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	es
dc.identifier.uri	https://hdl.handle.net/10550/79650
dc.description.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.	es
dc.title	When the state of the art is ahead of the state of understanding : unintuitive properties of deep neural networks	es
dc.type	journal article	es_ES
dc.subject.unesco		es
dc.identifier.doi		es
dc.type.hasVersion	VoR	es_ES