Parallel Hyperparameter Tuning of Accuracy for Deep Learning based Tornado Predictions
| dc.contributor.author | Basalyga, Jonathan N. | |
| dc.date.accessioned | 2020-07-28T18:05:33Z | |
| dc.date.available | 2020-07-28T18:05:33Z | |
| dc.description | UMBC High Performance Computing Facility | en_US |
| dc.description.abstract | Predicting violent storms and dangerous weather conditions with current physics based weather models can take a long time due to the immense complexity associated with numerical simulations. Machine learning has the potential to classify tornadic weather patterns much more rapidly, thus allowing for more timely alerts to the public. In this work, we examine what impact varying the batch size and the number of GPUs a convolutional neural network is trained on has on the network’s accuracy at classifying storm data. We conclude that using multiple GPUs to train a single network has no significant advantage over using a single GPU. Therefore, multiple GPUs should instead be used to maximize search throughput by using each of them simultaneously for single GPU runs or to solve larger problems by pooling their memory. | en_US |
| dc.description.sponsorship | We thank Carlos Barajas for providing the code used to run the studies done in this work. He also provided a great deal of guidance and patiently explained the trickier aspects of neural networks. We also thank Dr. Matthias K. Gobbert for his mentoring and support over the course of this work. This work is supported by the grant “CyberTraining: DSE: Cross-Training of Researchers in Computing, Applied Mathematics and Atmospheric Sciences using Advanced Cyberinfrastructure Resources” from the National Science Foundation (grant no. OAC–1730250). The hardware used in the computational studies is part of the UMBC High Performance Computing Facility (HPCF). The facility is supported by the U.S. National Science Foundation through the MRI program (grant nos. CNS–0821258, CNS–1228778, and OAC–1726023) and the SCREMS program (grant no. DMS– 0821311), with additional substantial support from the University of Maryland, Baltimore County (UMBC). See hpcf.umbc.edu for more information on HPCF and the projects using its resources. | en_US |
| dc.description.uri | http://hpcf-files.umbc.edu/research/papers/Basalyga_SeniorThesis2020.pdf | en_US |
| dc.format.extent | 9 pages | en_US |
| dc.genre | senior theses | en_US |
| dc.identifier | doi:10.13016/m2eu9l-tokn | |
| dc.identifier.citation | Jonathan N. Basalyga, Parallel Hyperparameter Tuning of Accuracy for Deep Learning based Tornado Predictions, http://hpcf-files.umbc.edu/research/papers/Basalyga_SeniorThesis2020.pdf | en_US |
| dc.identifier.uri | http://hdl.handle.net/11603/19257 | |
| dc.language.iso | en_US | en_US |
| dc.publisher | UMBC | en_US |
| dc.relation.isAvailableAt | The University of Maryland, Baltimore County (UMBC) | |
| dc.relation.ispartof | UMBC Mathematics Department Collection | |
| dc.relation.ispartof | UMBC Faculty Collection | |
| dc.relation.ispartof | UMBC Student Collection | |
| dc.rights | This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author. | |
| dc.subject | UMBC High Performance Computing Facility (HPCF) | |
| dc.title | Parallel Hyperparameter Tuning of Accuracy for Deep Learning based Tornado Predictions | en_US |
| dc.type | Text | en_US |