A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2007.13657v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Towards Learning Convolutions from Scratch
[article]
<span title="2020-07-27">2020</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Convolution is one of the most essential components of architectures used in computer vision. As machine learning moves towards reducing the expert bias and learning it from data, a natural next step seems to be learning convolution-like structures from scratch. This, however, has proven elusive. For example, current state-of-the-art architecture search algorithms use convolution as one of the existing modules rather than learning it from data. In an attempt to understand the inductive bias
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.13657v1">arXiv:2007.13657v1</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kkkqf3vigrfxhabsagr7oxe5wq">fatcat:kkkqf3vigrfxhabsagr7oxe5wq</a>
</span>
more »
... gives rise to convolutions, we investigate minimum description length as a guiding principle and show that in some settings, it can indeed be indicative of the performance of architectures. To find architectures with small description length, we propose β-LASSO, a simple variant of LASSO algorithm that, when applied on fully-connected networks for image classification tasks, learns architectures with local connections and achieves state-of-the-art accuracies for training fully-connected nets on CIFAR-10 (85.19 bridging the gap between fully-connected and convolutional nets.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200730211747/https://arxiv.org/pdf/2007.13657v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.13657v1" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>