Name
Abstract | ||
|---|---|---|
We propose a new scalable method to optimize the architecture of an artificial neural network. The proposed algorithm, called Greedy Search for Neural Network Architecture, aims to determine a neural network with minimal number of layers that is at least as performant as neural networks of the same structure identified by other hyperparameter search algorithms in terms of accuracy and computational cost. Numerical results performed on benchmark datasets show that, for these datasets, our method outperforms state-of-the-art hyperparameter optimization algorithms in terms of attainable predictive performance by the selected neural network architecture, and time-to-solution for the hyperparameter optimization to complete. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1016/j.parco.2021.102788 | PARALLEL COMPUTING |
Keywords | DocType | Volume |
Deep learning, Hyperparameter optimization, Neural network architecture, Random search, Greedy constructive algorithms, Adaptive algorithms | Journal | 104 |
ISSN | Citations | PageRank |
0167-8191 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Massimiliano Lupo Pasini | 1 | 4 | 1.54 |
| Junqi Yin | 2 | 0 | 1.01 |
| Ying Wai Li | 3 | 0 | 0.34 |
| Markus Eisenbach | 4 | 9 | 4.17 |