The performance of a Convolutional Neural Network (CNN) depends on its hyperparameters, like the number of layers, kernel sizes, or the learning rate for example. Especially in smaller networks and applications with limited computational resources, optimisation is key. We present a fast and efficient approach for CNN architecture selection. Taking into account time consumption, precision and robustness, we develop a heuristic to quickly and reliably assess a network's performance. In combination with Bayesian optimisation (BO), to effectively cover the vast parameter space, our contribution offers a plain and powerful architecture search for this machine learning technique.
@article{arxiv.1905.01924,
title = {Fast and Reliable Architecture Selection for Convolutional Neural Networks},
author = {Lukas Hahn and Lutz Roese-Koerner and Klaus Friedrichs and Anton Kummert},
journal= {arXiv preprint arXiv:1905.01924},
year = {2019}
}
Comments
As published in the proceedings of the 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), pages 179-184, Bruges 2019. 6 pages, 2 figures, 1 table