Efficient Learning Algorithms with Limited Resources
A special issue of Algorithms (ISSN 1999-4893). This special issue belongs to the section "Evolutionary Algorithms and Machine Learning".
Deadline for manuscript submissions: closed (1 May 2024) | Viewed by 1381
Special Issue Editors
Interests: computer vision; medical image processing
Special Issue Information
Dear Colleagues,
Machine Learning has recently achieved significant accomplishments across a diverse array of application domains (e.g., computer vision). Nonetheless, these achievements are heavily contingent upon substantial reservoirs of data and computational resources. This dependence poses a challenge in most real-world scenarios where data and computation resources are scarce. Our goal is to confront this challenge by devising effective strategies for implementing machine learning under conditions of limited resources, encompassing data, models, and knowledge. Consequently, researchers across various fields have turned their attention to the exploration of efficient learning methodologies. These methodologies encompass three key dimensions:
- Efficient data processing algorithm, which involves techniques such as lossy or lossy coding.
- Efficient model processing algorithm, which practices such as channel pruning and neural architecture search to enhance computational efficiency.
- Efficient knowledge transferring algorithm, as exemplified by transfer learning techniques including knowledge distillation that leverage existing knowledge effectively.
We extend an invitation to experts not only from these specific domains but also from related fields to engage in collaborative efforts and put forth groundbreaking methodologies. We hold a particular interest in receiving proposals that compose multiple themes mentioned above. For instance, we strongly encourage the exploration of integrated approaches that merge data and machine efficiency, employing compressed networks to reduce data volume. We believe such innovative methodologies harbor the potential to reshape the trajectory of machine learning and its applications, spanning realms such as computer vision and natural language processing. By addressing the formidable challenges posed by resource limitations, we aspire to make substantial contributions to the broader research community.
Dr. Luping Zhou
Guest Editor
Dr. Zhenghao Chen
Guest Editor Assistant
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. Algorithms 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 1600 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.
Keywords
- data compression
- model compression
- transfer learning
- image and video coding
- knowledge distillation
- zero/few-short learning
- neural architecture search
- channel pruning
