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
- Inici
- Investigació
- Revistes
- Mètode Science Studies Journal : Annual Review
- Mètode Science Studies Journal : Annual Review. 2019. Issue 9
- Visualitza element
IMPORTANT: Aquest repositori està en una versió antiga des del 3/12/2023. La nova instal.lació está en https://roderic.uv.es/
When the state of the art is ahead of the state of understanding : unintuitive properties of deep neural networks
Mostra el registre complet de l'element
|
Visualització
|
| Serrà, Joan | |||
| Aquest document és un/a article, creat/da en: 2019 | |||
|
|||
| 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. | |||
| Veure al catàleg Trobes | |||