Fast and Reliable Architecture Selection for Convolutional Neural Networks
This work addresses the need for efficient architecture selection in CNNs, particularly for applications with limited resources, though it appears incremental as it builds on existing Bayesian optimization techniques.
The paper tackles the problem of efficiently selecting optimal CNN architectures under computational constraints by developing a fast heuristic for performance assessment combined with Bayesian optimization, resulting in a method that quickly and reliably covers the vast parameter space.
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.