Loading...
Please wait, while we are loading the content...
Optimizing deep learning hyper-parameters through an evolutionary algorithm
| Content Provider | ACM Digital Library |
|---|---|
| Author | Karnowski, Thomas P. Rose, Derek C. Young, Steven R. Lim, Seung-Hwan Patton, Robert M. |
| Abstract | There has been a recent surge of success in utilizing Deep Learning (DL) in imaging and speech applications for its relatively automatic feature generation and, in particular for convolutional neural networks (CNNs), high accuracy classification abilities. While these models learn their parameters through data-driven methods, model selection (as architecture construction) through hyper-parameter choices remains a tedious and highly intuition driven task. To address this, Multi-node Evolutionary Neural Networks for Deep Learning (MENNDL) is proposed as a method for automating network selection on computational clusters through hyper-parameter optimization performed via genetic algorithms. |
| Starting Page | 1 |
| Ending Page | 5 |
| Page Count | 5 |
| File Format | |
| ISBN | 9781450340069 |
| DOI | 10.1145/2834892.2834896 |
| Language | English |
| Publisher | Association for Computing Machinery (ACM) |
| Publisher Date | 2015-11-15 |
| Publisher Place | New York |
| Access Restriction | Subscribed |
| Subject Keyword | Deep learning Hyper-parameter optimization Evolutionary algorithm Convolutional neural networks |
| Content Type | Text |
| Resource Type | Article |
