Recent Progress in Explainable Artificial Intelligence and Low-Power Machine Learning

Dear Colleagues,

In recent years, there has been a notable surge in the popularity of explainable AI and low-power machine-learning techniques. Despite achieving remarkable performance, many AI models, such as deep-learning approaches, often remain impenetrable to human understanding, earning them the moniker "black boxes". This lack of transparency hinders our ability to comprehend the rationale behind AI-driven decisions, raising concerns about accountability, ethics, and trustworthiness. Furthermore, the extensive computational demands of most advanced AI systems contribute to a significant carbon footprint, exacerbating environmental concerns. In response to these challenges, we are pleased to announce a Special Issue dedicated to exploring recent advancements in explainable AI and low-power machine-learning techniques. This interdisciplinary endeavor aims to foster research and development across diverse fields, shedding light on the following key areas:

1. Advancements in Explainable AI:

• Design and development of novel human-explainable AI models.
• Novel methodologies for enhancing the interpretability and transparency of AI models.
• Applications of explainable AI in real-world scenarios, such as healthcare, finance, and autonomous systems.

2. Innovations in Low-Power Machine Learning:

• Design and development of energy-efficient algorithms and architectures for training and/or inference in machine learning models.
• Applications of low-power machine learning in resource-constrained environments, such as embedded systems, Internet of Things (IoT) devices, and edge computing platforms.

Through this Special Issue, we aim to facilitate the exchange of ideas and insights among researchers, practitioners, and policymakers working at the forefront of explainable AI and low-power machine learning. We invite original research papers, review articles, and case studies that contribute to advancing our understanding of these crucial areas and their applications in solving complex problems.

Prof. Dr. Ole-Christoffer Granmo
Prof. Dr. Lei Jiao
Prof. Dr. Rishad Shafik
Prof. Dr. Alex Yakovlev
Guest Editors

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 100 words) can be sent to the Editorial Office for announcement on this website.

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-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics 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 2400 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.

• explainable and transparent AI
• interpretability
• human-understandable AI
• low-power machine learning
• energy-efficient AI
• AI for IoT and edge computing
• embedded AI