In recent years, Deep Learning has become the go-to solution for a broad range of applications, often outperforming state-of-the-art. However, it is important, for both theoreticians and practitioners, to gain a deeper understanding of the difficulties and limitations associated with common approaches and algorithms. We describe four types of simple problems, for which the gradientbased algorithms commonly used in deep learning either fail or suffer from significant difficulties. We illustrate the failures through practical experiments, and provide theoretical insights explaining their source, and how they might be remedied.
|Original language||American English|
|Title of host publication||34th International Conference on Machine Learning, ICML 2017|
|Publisher||International Machine Learning Society (IMLS)|
|Number of pages||15|
|State||Published - 2017|
|Event||34th International Conference on Machine Learning, ICML 2017 - Sydney, Australia|
Duration: 6 Aug 2017 → 11 Aug 2017
|Name||34th International Conference on Machine Learning, ICML 2017|
|Conference||34th International Conference on Machine Learning, ICML 2017|
|Period||6/08/17 → 11/08/17|
Bibliographical notePublisher Copyright:
Copyright © 2017 by the author(s).