Notwithstanding the recent successes of deep convolutional neural networks for classification tasks, they are sensitive to the selection of their hyperparameters, which impose an exponentially large search space on modern convolutional models. Traditional hyperparameter selection methods include manual, grid, or random search, but these require expert knowledge or are computationally burdensome. Divergently, Bayesian optimization and evolutionary inspired techniques have surfaced as viable alternatives to the hyperparameter problem. Thus, an alternative hybrid approach that combines the advantages of these techniques is proposed. Specifically, the search space is partitioned into discrete-architectural, and continuous and categorical hyperparameter subspaces, which are respectively traversed by a stochastic genetic search, followed by a genetic-Bayesian search. Simulations on a prominent image classification task reveal that the proposed method results in an overall classification accuracy improvement of 0.87% over unoptimized baselines, and a greater than 97% reduction in computational costs compared to a commonly employed brute force approach. / Electrical and Mining Engineering / M. Tech. (Electrical Engineering)
| Identifer | oai:union.ndltd.org:netd.ac.za/oai:union.ndltd.org:unisa/oai:uir.unisa.ac.za:10500/24977 |
| Date | 01 1900 |
| Creators | Rawat, Waseem |
| Contributors | Wang, Zenghui |
| Source Sets | South African National ETD Portal |
| Language | English |
| Detected Language | English |
| Type | Dissertation |
| Format | 1 online resources (xv, 150 leaves) : illustrations (some color), graphs (some color) |
Page generated in 0.0016 seconds