Call for Nominations for Various Officer Positions and ADCOM Members-at-Large

The IEEE Computational Intelligence Society (CIS) is seeking nominations for the following key leadership positions (terms are in parentheses):

According to the CIS Bylaws, ARTICLE XII – GOVERNANCE AND ADMINISTRATION,

Section 35 - Schedule for ADCOM Elections:

"Five ADCOM Members-at-Large are elected each year, plus any vacated positions."

"The election of Vice President for Conferences, Vice President for Finances, Vice President for Technical Activities, and Vice President for Industrial and Governmental Activities shall take place in odd-numbered years."

ARTICLE XIV Section 2 (h) - "Office shall be assumed by the Vice President for Finances on January 1 of the second year immediately following his/her election."

Eligibility requirements are defined in the CIS Bylaws, ARTICLE XIV – NOMINATIONS, ELECTIONS AND APPOINTMENTS.

The nomination will close on 1 May 2023.

For more information on eligibility, submission requirements, and deadlines, please visit our website for the official call for nominations.

The IEEE Computational Intelligence Society annually recognizes significant contributions and meritorious service in the field of computational intelligence.

Nominations are highly encouraged to recognize our volunteers and eminent colleagues to keep our Society alive and to promote research excellence in computational intelligence. The IEEE Computational Intelligence Society sponsors several annual Awards. Please see the awards and nomination details on the IEEE CIS Awards page.

The IEEE CIS Awards have a deadline of 30 April 2023 (strict deadline). 

The IEEE Computational Intelligence Society sponsors many conferences each year. We are currently soliciting proposals for the following upcoming conferences:

• 2025 IEEE Congress on Evolutionary Computation (IEEE CEC 2025)
• 2025 FUZZ-IEEE Conference (FUZZ-IEEE 2025)
• 2026 IEEE World Congress on Computational Intelligence (WCCI 2026)

IEEE CEC 2025 and FUZZ-IEEE 2025 are the society’s flagship conferences for evolutionary computation and fuzzy systems respectively. WCCI 2026 combines these conferences with the International Joint Conference on Neural Networks, our flagship conference on neural networks.

CEC 2023 will be held in the USA. FUZZ-IEEE 2023 will be held in Korea. IEEE WCCI 2024 will be held in Japan. We are hopeful that some bids will be submitted from other geographical areas.

Proposals for the IEEE CEC 2025 and FUZZ-IEEE 2025 conferences should be submitted by 30 April 2023. Proposals for IEEE WCCI 2026 conference should be submitted by 30 June 2023 (hard deadlines). This will provide sufficient time for review and decision by IEEE CIS Conferences Committee and Administrative Committee.

Please inform VP Conferences, Marley Vellasco ([email protected]) and Chair of the Confcom Subcommittee on Future Conferences, Steven Corns ([email protected])of your intention to provide a proposal or if you would like further information. The process for generating such a proposal can be found on our website.

Wiley-IEEE Press invites nominations for two book awards to recognize the authors of an outstanding textbook and an outstanding professional book published by Wiley-IEEE Press. Submission of Nominations Nominations may be submitted via our nominations site. The deadline is no later than 5 May 2023.

For information on how to nominate, visit our website. Any questions should be directed to [email protected].

Please note that only IEEE members can submit a nomination.

Distinguished Lecturers present novel basic and/or applied research results in their CIS sub-field. Their lectures offer insights into the trends and challenges of their CIS sub-field and their vision for the given sub-field. This year we have 19 lecturers in various CIS sub-fields. 

The program supports local CIS Chapters by enabling a major Chapter event which can considerably improve a Chapter’s visibility to their existing IEEE CIS members, other IEEE Society members and the wider CIS community in their area. For more details on the  process of organizing distinguished lectures please click here.

It should be noted that this program is NOT intended as a means to finance speakers for conferences/workshops or symposia.

Please visit the Distinguished Lectureres Program for more information. 

IEEE CIS has approved a new Technical Committee known as SHIELD which looks at the Ethical, Legal, Social, Environmental and Human Dimensions of CI and AI. The aim of this Technical Committee is to create a vibrant environment within the IEEE Computational Intelligence Society (CIS) to provide a platform to bring together the many dimensions (not limited to ethical, social, legal, economic, cultural, environmental, and human) which are required to research, innovate, develop, and deploy responsible and trustworthy CI/AI for humanity.

Computational Intelligence (CI) and Artificial Intelligence (AI), specifically the ethics around its development and application – has become a contentious issue and the subject of intense political, regulatory, and societal debate. CI/AI researchers in both academia and industry excel in designing state of the art technologies and bringing them into life to create significant positive impacts on society but there are many challenges on a number of different dimensions. Ethics cover the moral principles that govern the behaviour of the technology, as well as the designer. Social responsibility is the duty of everyone – in this context CI/AI researchers – to minimize the ecological footprint of these technologies and balance the size of this footprint with economic benefits. Social justice raises important questions on the impact of automation on the workforce and the possible implications of that on distribution of wealth within societies. There is a need to upskill many users, so that they confident in being able to question automated and semi-automated decision-making systems Privacy affords individuals with the freedom to choose which self-traits to share if consent processes are clear and understood. The boundaries between law and ethics are often grey areas in determining what is a low risk compared to a high-risk system and the consequential impact on individuals and society. Responsibility and accountability needs to be embodied into AI Governance and the diversity of human-centred design needs to be a consideration in research design. In the data driven and AI products and services, specifically that utilise computer vision and natural langue processing, that we research, design and implement, consideration needs to be given to the environmental impact with regards to the energy consumption required to develop efficient solutions (red verses green AI). From an economic perspective, AI and the associated forthcoming global legalisation will have a disruptive impact on the economy, that will be geographically imbalanced (developed verses developing countries), potentially leading to increases in inequality. The SHIELD Technical Committee aims to explore some of these issues and challenges from many viewpoints.

This technical committee has five main goals:

(1) To create a vibrant environment within IEEE CIS to innovate, implement and evaluate the ethical, social, legal, economic, cultural, environmental, and human dimensions of AI/CI on society.

(2) To examine how trust in CI/AI can be achieved through stakeholder engagement and co-production in research and innovation.

(3) To continually review (and provide opinion on) current and emerging global legalisation and standards in the field of AI and data driven technologies

(4) To promote and organise technical activities (special sessions, panel discussions, special issues, workshops, etc) on the ethical, social, legal, economic, environmental, and human dimensions of CI/AI technologies

(5) To instigate change in the professional practice of researchers through consequence scanning practices and the embedding of ethical practices as a norm.

Graph Lifelong Learning: A Survey

Graph learning is a popular approach for performing machine learning on graph-structured data. It has revolutionized the machine learning ability to model graph data to address downstream tasks. Its application is wide due to the availability of graph data ranging from all types of networks to information systems. Most graph learning methods assume that the graph is static and its complete structure is known during training. This limits their applicability since they cannot be applied to problems where the underlying graph grows over time and/or new tasks emerge incrementally. Read More

IEEE Computational Intelligence Magazine, February 2023

Detecting Adversarial Examples by Input Transformations, Defense Perturbations, and Voting

Over the past few years, convolutional neural networks (CNNs) have proved to reach superhuman performance in visual recognition tasks. However, CNNs can easily be fooled by adversarial examples (AEs), i.e., maliciously crafted images that force the networks to predict an incorrect output while being extremely similar to those for which a correct output is predicted. Regular AEs are not robust to input image transformations, which can then be used to detect whether an AE is presented to the network. Nevertheless, it is still possible to generate AEs that are robust to such transformations. This article extensively explores the detection of AEs via image transformations and proposes a novel methodology, called defense perturbation, to detect robust AEs with the same input transformations the AEs are robust to. Read More

IEEE Transactions on Neural Networks and Learning Systems, March 2023

Fuzzy-Based Optimization and Control of a Soft Exosuit for Compliant Robot–Human–Environment Interaction

Many previous studies of soft exosuits improved human locomotion performance. However, there is no example to control a soft exosuit using human ankle impedance adaption in assistance tasks compliantly. In this article, the human–environment interaction information is exploited into the exosuit control. A novel fuzzy-based optimization and control method of soft exosuit is proposed to provide plantarflexion assistance for human walking by changing the human–robot interaction. In particular, a fuzzy neurodynamics optimization is developed to learn the unknown human ankle impedance parameters automatically.  Read more

IEEE Transactions on Fuzzy Systems, January 2023

PRE-NAS: Evolutionary Neural Architecture Search With Predictor

Neural architecture search (NAS) aims to automate architecture engineering in neural networks. This often requires a high computational overhead to evaluate a number of candidate networks from the set of all possible networks in the search space. Prediction of the performance of a network can alleviate this high computational overhead by mitigating the need for evaluating every candidate network. Developing such a predictor typically requires a large number of evaluated architectures which may be difficult to obtain. We address this challenge by proposing a novel evolutionary-based NAS strategy, predictor-assisted evolutionary NAS (PRE-NAS) which can perform well even with an extremely small number of evaluated architectures. Read More

IEEE Transactions on Evolutionary Computation, February 2023

Enhanced Rolling Horizon Evolution Algorithm With Opponent Model Learning: Results for the Fighting Game AI Competition

We present concepts and recipes for the anytime performance assessment when bThe Fighting Game AI Competition (FTGAIC) provides a challenging benchmark for two-player video game artificial intelligence. The challenge arises from the large action space, diverse styles of characters and abilities, and the real-time nature of the game. In this article, we propose a novel algorithm that combines the rolling horizon evolution algorithm (RHEA) with opponent model learning. The approach is readily applicable to any two-player video game. In contrast to conventional RHEA, an opponent model is proposed and is optimized by supervised learning with cross-entropy and reinforcement learning with policy gradient and Q-learning respectively, based on history observations from opponent. Read More

IEEE Transactions on Games, March 2023

PSNet: Parallel Symmetric Network for Video Salient Object Detection

For the video salient object detection (VSOD) task, how to excavate the information from the appearance modality and the motion modality has always been a topic of great concern. The two-stream structure, including an RGB appearance stream and an optical flow motion stream, has been widely used as a typical pipeline for VSOD tasks, but the existing methods usually only use motion features to unidirectionally guide appearance features or adaptively but blindly fuse two modality features. However, these methods underperform in diverse scenarios due to the uncomprehensive and unspecific learning schemes. In this paper, following a more secure modeling philosophy, we deeply investigate the importance of appearance modality and motion modality in a more comprehensive way and propose a VSOD network with up and down parallel symmetry, named PSNet. Read More

IEEE Transactions on Emerging Topics in Computational Intelligence, April 2023

• IEEE TNNLS Special Issue on Deep Learning: When and How? (23 April 2023 )
• IEEE TNNLS Special issue on Trustworthy Federated Learning (1 June 2023)
• IEEE TAI Special Issue on AutoML for Non-Stationary Data (2 June 2023)
• IEEE TAI  IEEE TEVC Special Issue on Evolutionary Neural Architecture Search (30 June 2023)
• IEEE TNNLS Special Issue on Graph Learning (1 July 2023)
• IEEE TFS Special Issue on Fuzzy Systems Toward Human-Inspired Computational Intelligence in Complex Systems (31 October 2023)
• IEEE TFS Special Issue on Smart Fuzzy Optimization in Sustainable Manufacturing and Supply Chain Management (1 November 2023)
• IEEE TFS Special Issue on Fuzzy-Deep Neural Network Learning in Sentiment Analysis (15 January 2024)

2023 IEEE Conference on Artifical Intelligence (2023 IEEE CAI) Call for Participation

The IEEE Conference on Artificial Intelligence (IEEE CAI) will take place in Santa Clara, CA, USA on 5-6 June 2023. This new conference series emphasizes AI applications in specific verticals that impact industrial technology and innovation. Key verticals include Energy, Healthcare and Life Science, Transportation and Aerospace, Earth Systems Decision Support, Industrial AI, and Ethical and Societal Implications of AI. IEEE CAI seeks original, high-quality poster papers describing the research and results that contribute to advancements in AI applications. Access all submission details here. 

IEEE 2023 Congress on Evolutionary Computation

IEEE CEC 2023 is a world-class conference that brings together researchers and practitioners in the field of evolutionary computation and computational intelligence from around the globe. The conference program includes plenary lectures, regular and special sessions, tutorials, competitions, workshops and panel discussions. IEEE CEC 2023 is calling for Call for Late Breaking Papers and Journal to Conference (J2C) Papers.