Interpretable Models and Their Applications in Neural Computation and Statistical Learning

Dear Colleagues,

Neural networks and machine learning models have recently developed very fast and achieved the best results for many practical applications in AI and related fields. Although the advanced neural network models can effectively solve many challenging problems with complicated and deep architectures, they are generally designed by experience and cannot be theoretically interpreted. This has strongly limited their application and developments. Therefore, model interpretability analysis, as well as interpretable model design in neural computation and statistical learning, has become important and necessary. It is clear that model interpretability can be discovered by mathematical analysis under a statistical or probability framework. On the other hand, the data should be assumed to be generated from a probability model. Moreover, model interpretability should focus on a certain kind of practical problem for data analysis and mining.

The aim of this Special Issue is to publish original research articles covering advances in model interpretability and interpretable models in neural computation and statistical learning. Potential topics include but are not limited to the following: interpretable deep learning models; Gaussian processes and their mixtures; curve clustering analysis and prediction; and automated model selection.

Prof. Dr. Jinwen Ma
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. Mathematics is an international peer-reviewed open access semimonthly 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 2600 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.