Abstract | ||
---|---|---|
In this paper, traditional and meta-heuristic approaches for optimizing deep neural networks (DNN) have been surveyed, and a genetic algorithm (GA)-based approach involving two optimization phases for hyper-parameter discovery and optimal data subset determination has been proposed. The first phase aims to quickly select an optimal combination of the network hyper-parameters to design a DNN. Compared to the traditional grid-search-based method, the optimal parameters have been computed 6.5 times faster for recurrent neural network (RNN) and 8 times faster for convolutional neural network (CNN). The proposed approach is capable of tuning multiple hyper-parameters simultaneously. The second phase finds an appropriate subset of the training data for near-optimal prediction performance, providing an additional speedup of 75.86% for RNN and 41.12% for CNN over the first phase. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1007/s00500-021-05770-w | SOFT COMPUTING |
Keywords | DocType | Volume |
Deep Neural Network, Hyper-parameter, Genetic Algorithm, Recurrent Neural Network, Streaming Data Prediction, Convolution Neural Network, Image Recognition | Journal | 25 |
Issue | ISSN | Citations |
13 | 1432-7643 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Puneet Kumar | 1 | 5 | 0.77 |
Shalini Batra | 2 | 0 | 0.34 |
Balasubramanian Raman | 3 | 679 | 70.23 |