| | |
| | |
Stat |
Members: 3645 Articles: 2'500'096 Articles rated: 2609
19 April 2024 |
|
| | | |
|
Article overview
| |
|
Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias | Stéphane d'Ascoli
; Levent Sagun
; Joan Bruna
; Giulio Biroli
; | Date: |
16 Jun 2019 | Abstract: | Despite the phenomenal success of deep neural networks in a broad range of
learning tasks, there is a lack of theory to understand the way they work. In
particular, Convolutional Neural Networks (CNNs) are known to perform much
better than Fully-Connected Networks (FCNs) on spatially structured data: the
architectural structure of CNNs benefits from prior knowledge on the features
of the data, for instance their translation invariance. The aim of this work is
to understand this fact through the lens of dynamics in the loss landscape.
We introduce a method that maps a CNN to its equivalent FCN (denoted as
eFCN). Such an embedding enables the comparison of CNN and FCN training
dynamics directly in the FCN space. We use this method to test a new training
protocol, which consists in training a CNN, embedding it to FCN space at a
certain ’switch time’ $t_w$, then resuming the training in FCN space. We
observe that for all switch times, the deviation from the CNN subspace is
small, and the final performance reached by the eFCN is higher than that
reachable by the standard FCN. More surprisingly, for some intermediate switch
times, the eFCN even outperforms the CNN it stemmed from. The practical
interest of our protocol is limited by the very large size of the highly sparse
eFCN. However, it offers an interesting insight into the persistence of the
architectural bias under the stochastic gradient dynamics even in the presence
of a huge number of additional degrees of freedom. It shows the existence of
some rare basins in the FCN space associated with very good generalization.
These can be accessed thanks to the CNN prior, and are otherwise missed. | Source: | arXiv, 1906.6766 | Services: | Forum | Review | PDF | Favorites |
|
|
No review found.
Did you like this article?
Note: answers to reviews or questions about the article must be posted in the forum section.
Authors are not allowed to review their own article. They can use the forum section.
browser Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)
|
| |
|
|
|
| News, job offers and information for researchers and scientists:
| |