- Submissions Due: 15 October 2022
- Initial Notification (Accept/Reject/Revise, Tentative): 15 January 2023
- Revisions Due: 15 March 2023
- Final Notifications (Tentative): 1 May 2023
Publication (Tentative): After July 2023
Computing has become very pervasive in today’s society, so applications have diverse sets of requirements. For example, many applications can tolerate a specific degree of incorrectness (i.e., a decrease in accuracy) in the results, such as (1) the input data itself is inaccurate due to noise (as occurring at the input of a sensor); (2) systems inherently generate non-unique results, or a range of outputs are generally acceptable (such as search engines), and (3) in human recognition of images and sounds, a certain degree of accuracy loss is almost indistinguishable compared with the exact results. Therefore, a wide range of error-resilient applications (such as multimedia, signal processing, machine learning, pattern recognition, probabilistic data structures and data mining) can readily generate an approximate result provided the loss in accuracy is kept within tolerable ranges. Approximate processing has been proposed as a paradigm for efficient and low-power design at nanoscales; such paradigm generates and stores good enough results rather than consistently fully accurate. Therefore, novel techniques for approximation have received significant attention from both research and industrial communities in the past few years and have been studied at several levels, including hardware, software/algorithms, programming languages, logic synthesis, and automated design processes.
This special section is devoted to covering: 1) recent advances in hardware, algorithms, and implementations for error-resilient (approximate) systems and 2) techniques for approximation focusing on storage/memory, data computation, and advanced designs of data processing systems. Relevant topics of interest to this special section include (but are not limited to):
- Fundamental principles and techniques for approximate computing
- Approximate schemes for data storage and related schemes, such as in-memory computing
- Schemes for approximation in compiler, programming language, and software layer design
- Approximate arithmetic computation using new number formats
- Evaluation methods and error analysis of approximate systems
- Logic synthesis/ EDA tools for approximate computing/storage designs
- Hardware reliability/security for approximate computing/storage systems
- Approximate schemes for emerging computing paradigms (such as stochastic, machine learning, probabilistic, and big data)
- Novel applications of approximate data processing
For author information and guidelines on submission criteria, please visit IEEE TETC‘s Author Information page. Please submit papers through the ScholarOne system, and be sure to select the special-section name. Manuscripts should not be published or currently submitted for publication elsewhere. Please submit only full papers intended for review, not abstracts, to the ScholarOne portal.
Please contact the guest editors at firstname.lastname@example.org.
Ke Chen, Nanjing University of Aeronautics and Astronautics, China (IEEE Member)
Shanshan Liu, New Mexico State University, USA (IEEE Member)
Weiqiang Liu, Nanjing University of Aeronautics and Astronautics, China (IEEE Senior Member)
Fabrizio Lombardi, Northeastern University, USA (IEEE Fellow)
Corresponding TETC Editor: Nader Bagherzadeh, University of California at Irvine, USA (IEEE Fellow)