Evolutionary Deep Fusion Method and its Application in Chemical Structure Recognition

Feature extraction is a critical issue in many machine learning systems. A number of basic fusion operators have been proposed and studied. This article proposes an evolutionary algorithm, called evolutionary deep fusion method, for searching an optimal combination scheme of different basic fusion operators to fuse multiview features. We apply our proposed method to chemical structure recognition. Our proposed method can directly take images as inputs, and users do not need to transform images to other formats. The experimental results demonstrate that our proposed method can achieve a better performance than those designed by human experts on this real-life problem.

Automated summary

Feature extraction is crucial in machine learning systems, and the proposed evolutionary deep fusion method aims to search for an optimal combination of fusion operators for multiview features. Applied to chemical structure recognition, this method outperforms those designed by human experts, with the advantage of directly using images as inputs without requiring format transformation.