# Fast and Reliable Architecture Selection for Convolutional Neural Networks

## TL;DR

This paper introduces a fast, reliable method for selecting CNN architectures by combining a heuristic performance assessment with Bayesian optimisation, improving efficiency in resource-constrained scenarios.

## Contribution

It presents a novel heuristic combined with Bayesian optimisation for rapid and dependable CNN architecture selection, addressing computational efficiency and robustness.

## Key findings

- The approach reduces search time significantly.
- It maintains high accuracy and robustness.
- Effective in small networks and limited-resource environments.

## Abstract

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.