Transparency of Deep Neural Networks and Complex Tree Ensembles

Dear Colleagues,

Deep learning is a new branch of machine learning which has been proven to be a powerful feature extraction tool in computer vision. The primary disadvantage of deep learning and complex tree ensembles (CTEs) such as XGBoost is that they have no clear declarative representation of knowledge. In addition, deep learning and CTEs have considerable difficulties in generating the necessary explanation structures, which limits their potential because the ability to provide detailed characterizations of classification strategies would promote their acceptance. However, surprisingly, very little work has been carried out in relation to the transparency of deep learning and CTEs. Bridging this gap could be expected to contribute to the real-world utility of deep learning and CTEs. The transparency of deep neural networks is the first step towards filling this gap. The next step towards utilizing deep neural networks and CTEs is extracting rules from them. Transparency and rule extraction from deep neural networks and CTEs therefore remain areas in need of further innovation.

This Special Issue also focuses on the black box nature of deep neural networks and the transparency, interpretability and explainability of deep neural networks (DNNs) and complex tree ensembles (CTEs) such as gradient boosting decision tree, XGBoost, decision forest, and random forest. 

Prof. Dr. Yoichi Hayashi
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Machine Learning and Knowledge Extraction is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.