Machine and Deep Learning: Beyond Computational and Data-Related Limitations

Dear Colleagues,

While we have made tremendous progress in AI, some limitations prevent many approaches from reaching industrial applications. Considering these limitations, this Special Issue focuses on 1) computational limitations and 2) data-related limitations. The goal of the first axis is to focus on the software and hardware compression of neural networks of all types in order to reduce both the size of these networks and the inference time they need to produce their predictions. Those neural networks should be able to run on smaller devices, reducing the energetic consumption and avoiding data transfer through the network, which helps preserve its privacy and ensures the quality of service anywhere and anytime. The goal of the second axis is to study architectures that allows learning from 1) multimodal data, 2) unlabeled or weakly labeled data and 3) continuously arriving data, which requires learning throughout the life of the algorithm, providing convenient interpretation and explanation. Indeed, in real-life applications, if many data are available, these data are usually not labelled or biased, and they come from diverse sensors. Massive amounts of manual labeling and models that cannot adapt to novel data are not realistic. This Special Issue, therefore, aims to investigate innovative solutions to overcome two major obstacles in current AI technology: the lack of properly labeled data and the lack of storage and computational capacity on lightweight and embedded systems. We invite submissions from researchers addressing these two axes. We encourage authors to submit papers within different domains with or without industrial applications. This Special Issue aims to cover recent advances in DNN architecture compression and edge deployment on the one hand, and advances in unsupervised learning, self-/semi-supervised learning, multimodal learning, explainable deep learning, active learning and continuous learning on the other hand. Reviews and surveys on the state-of-the-art DNN architectures are also welcomed.  The topics of interest for this Special Issue include:

• DNN software compression;
• DNN hardware compression;
• DNN pruning and quantization;
• Knowledge distillation;
• Model deployment in edge and cloud architectures; 
• Edge artificial intelligence;
• Unsupervised learning;
• Semi-supervised and self-supervised learning;
• Active learning;
• Explainable deep learning;
• Continual learning;
• Knowledge transfer;
• Lifelong learning.

However, please do not feel limited by these topics; we will consider submissions in any related area. The Special Issue is linked to the TRAIL Institute for AI, Belgium, but is open to any submission.

Dr. Matei Mancas
Prof. Dr. Sidi Ahmed Mahmoudi
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.

• artificial intelligence
• machine and deep learning
• DNN compression
• knowledge distillation
• self-supervised learning
• active learning
• cloud and edge computing