Journal
PROCEEDINGS OF 2019 IEEE/ACM THIRD WORKSHOP ON DEEP LEARNING ON SUPERCOMPUTERS (DLS)
Volume -, Issue -, Pages 36-44Publisher
IEEE COMPUTER SOC
DOI: 10.1109/DLS49591.2019.00010
Keywords
deep learning; evolutionary algorithms; hyper-parameters; optimization; remote sensing; settlement mapping
Funding
- OLCF [GEO121]
Ask authors/readers for more resources
Deep-learner hyper-parameters, such as kernel sizes, batch sizes, and learning rates, can significantly influence the quality of trained models. The state of the art for finding optimal hyper-parameters generally uses a brute force, grid search approach, random search, or Bayesian-based optimization among other techniques. We applied an evolutionary algorithm to optimize kernel sizes for a convolutional neural network used to detect settlements in satellite imagery. Usually convolutional layer kernel sizes are small - typically one, three, or five - but we found that the system converged at, or near, kernel sizes of nine for the last convolutional layer, and that this occurred formultiple runs using two different datasets. Moreover, the larger kernel sizes had fewer false positives than the 3x3 kernel sizes found as optimal via a brute force uniform grid search. This suggests that this large kernel size may be leveraging patterns found in larger areal features in the source imagery, and that this may be generalized as possible guidance for similar remote sensing deep-learning tasks.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available