The Transformer-based methods provide a good opportunity for modeling the global context of gigapixel whole slide image (WSI), however, there are still two main problems in applying Transformer to WSI-based survival analysis task. First, the training data for survival analysis is limited, which makes the model prone to overfitting. This problem is even worse for Transformer-based models which require

I am deeply honored to serve as the President of the IEEE Computational Intelligence Society (CIS) for 2024-2025. I had never imagined that I would become the President of our society when I joined IEEE at the 1998 World Congress on Computational Intelligence. I would take this opportunity to thank Bernadette Bouchon-Meunier, chair of the nomination committee and her colleagues, for their trust. I

It is a great honor and a privilege for me to serve as the Vice President for Conferences of the IEEE Computational Intelligence Society (CIS). Conferences are one of the main avenues for Computational Intelligence (CI) researchers to interact with each other and exchange ideas for the advancement of the field. CIS has a long history of providing high-quality conferences on various CI topics for our

It is a real pleasure and privilege to have been elected to and to serve as Vice President for Technical Activities of the IEEE Computational Intelligence Society (CIS) for 2024 and 2025. CIS is a vibrant home for individuals from all walks of life who are passionate about the theory, design, application, and development of a broad range of artificially intelligent systems. Just as the technology,

He is author of the books “Artificial Neural Networks for Modelling and Control of Non-linear Systems” (Springer) and “Least Squares Support Vector Machines” (World Scientific), co-author of the book “Cellular Neural Networks, Multi-Scroll Chaos and Synchronization” (World Scientific) and editor of the books “Nonlinear Modeling: Advanced Black-Box Techniques” (Springer), “Advances in Learning Theory:

The IEEE Computational Society (CIS) offers many financially-sponsored conferences each year. All of these depend on the hard work and effort of volunteers who propose and then organize these events in the pursuit of a healthy exchange of information and improvement in the application and theory of computational intelligence approaches. The last few years in particular have been a challenging time

Thanks to the many submissions we have received, we can present this second part of our special issue on “AI-eXplained.” In here, we continue our mission to demystify the intricate world of artificial intelligence and make it accessible to a broader audience. As AI continues to evolve and integrate into various aspects of our lives, it becomes increasingly important to bridge the gap between experts

The beginning of a year is a good timing to conclude on what memorable moments have happened in the preceding year. Last summer, I was invited to give talks at the 2023 IEEE CIS Summer School and Summit Forum held at the Southern University of Science and Technology (SUSTech) in Shenzhen, China. Several IEEE CIS officers, Editors-in-Chief, and I gathered to introduce CI techniques and their advancements

Ai's role within the domain of Industrial IoT (IIoT) is somewhat obscured by other limelight-stealing feats of AI, such as the creation of convincing deep fakes featuring politicians or celebrities. However, the critical importance of IIoT in domains like consumer goods manufacturing, healthcare, power generation, and transportation mandates a closer examination of the new capabilities and pitfalls

Reports on the activities and discussions that were part of the Breaking Boundaries: Industry-Academia Workshop that took place on the 27th and 28th of June 2023 at Maastricht University in The Netherlands.

The IEEE Standards Association (SA) officially published the XES Standard as IEEE Std 1849-2016: IEEE Standard for eXtensible Event Stream (XES) for Achieving Interoperability in Event Logs and Event Streams on 11 November 2016. This standard has been sponsored by the IEEE Computational Intelligence Society (CIS) Standards Committee. Through the XES Standard, event data can be transported from the

“Large-scale multiobjective optimization problems (LSMOPs) are characterized as optimization problems involving hundreds or even thousands of decision variables and multiple conflicting objectives. To solve LSMOPs, some algorithms designed a variety of strategies to track Pareto-optimal solutions (POSs) by assuming that the distribution of POSs follows a low-dimensional manifold. However, traditional

This paper proposes an algorithm called Forward Composition Propagation (FCP) to explain the predictions of feed-forward neural networks operating on structured classification problems. In the proposed FCP algorithm, each neuron is described by a composition vector indicating the role of each problem feature in that neuron. Composition vectors are initialized using a given input instance and subsequently

Many real-world classification problems are becoming multi-label in nature, i.e., multiple class labels are assigned to an instance simultaneously. Multi-label classification is a challenging problem due to the involvement of three forms of interactions, i.e., feature-to-feature, feature-to-label, and label-to-label interactions. What further complicates the problem is that not all features are useful

Neuromorphic computing is an emerging research field that aims to develop new intelligent systems by integrating theories and technologies from multiple disciplines, such as neuroscience, deep learning and microelectronics. Various software frameworks have been developed for related fields, but an efficient framework dedicated to spike-based computing models and algorithms is lacking. In this work

Building and testing software for embedded systems can be challenging with an impact on delivery time, design reproducibility, and collaboration among project contributors. To accelerate project development, presented here is an automated build flow that utilizes Xilinx PetaLinux, and field programmable gate array (FPGA) hardware description and integrates with the GitLab continuous integration and

Recently, contrastive learning has shown its effectiveness in self-supervised learning by training features of augmentations of input images based on the contrastive loss. This paper aims to introduce contrastive learning and discuss the effects of augmentations, features, and parameters of contrastive learning. Interactive figures are developed to demonstrate the effective schemes proposed in contrastive

Fuzzy systems are known to provide not only accurate but also interpretable predictions. However, their explainability may be undermined if non-semantically grounded linguistic terms are used. Additional non-trivial challenges would arise if a prediction were to be explained counterfactually, i.e., in terms of hypothetical, non-predicted outputs. In this paper, we explore how both factual and counterfactual

In this paper, the idea of a fuzzy color and a fuzzy color space is shown in an interactive way. It is proposed several interactive elements, where readers can understand the different steps to build them. Furthermore, these elements allow the user to test with his/her own images via the behavior of the fuzzy colors.

Recently, contrastive learning has shown its effectiveness in self-supervised learning by training features of augmentations of input images based on the contrastive loss. This paper aims to introduce contrastive learning and discuss the effects of augmentations, features, and parameters of contrastive learning. Interactive figures are developed to demonstrate the effective schemes proposed in contrastive

* Denotes a CIS-Sponsored Conference

One year ago, CIM published the inaugural AI-eXplained (AI-X) immersive article on IEEE Xplore. It is thrilled to witness that our call for the new form of content representation has been responded to with tremendous passion and a surge of submissions. With great efforts, CIM offers a platform for delivering Al/CI concepts, designs, and applications via a vivid and innovative means of knowledge distribution

Wow, how time flies. It seems like only yesterday that I was writing my welcome column as your new President in the first issue of the 2022 CIM. Now it's time to hand over the reins to the 2024-2025 CIS President, Yaochu Jin. Yaochu will do a great job for CIS. It's been a great privilege and honor for me to serve as President, and really, it's been a blast. Both the field of computational intelligence

The inaugural 2023 IEEE Conference on Artificial Intelligence was held June 5-6 at the Hyatt Regency Santa Clara in California's Silicon Valley. This new event was several years in the making and included co-sponsorship by four IEEE societies including the IEEE Computational Intelligence Society (as lead organization for the first two years), IEEE Computer Society, IEEE Signal Processing Society, and

Recounts the career and contributions of Michio Sugeno.

Building energy management usually involves a number of objectives, such as investment costs, thermal comfort, system resilience, battery life, and many others. However, most existing studies merely consider optimizing less than three objectives since it becomes increasingly difficult as the number of objectives increases. In addition, the optimization of building energy management relies heavily on

The prior domain knowledge, i.e., the regularity property of continuous multiobjective optimization problems (MOPs), could be learned to guide the search for evolutionary multiobjective optimization. This paper proposes a learning-to-guide strategy (LGS) for assisting the search for multiobjective optimization algorithms in dealing with MOPs. The main idea behind LGS is to capture the regularity via

The Multi-Depot Capacitated Arc Routing Problem (MDCARP) is an important combinatorial optimization problem with wide applications in logistics. Large Scale MDCARP (LSMDCARP) often occurs in the real world, as the problem size (e.g., number of edges/tasks) is usually very large in practice. It is challenging to solve LSMDCARP due to the large search space and complex interactions among the depots and

As we witness the remarkable progress of artificial intelligence (AI) over the last decade, its potential to address real-world complexities and revolutionize various fields has become evident. From image processing to natural language translation, AI solutions have accomplished significant milestones. However, the growing importance of AI in diverse domains has raised the need for making this complex

This article aims to exemplify best-response dynamics and multi-agent online learning by group formation. This extended abstract provides a summary of the full paper in IEEE Computational Intelligence Magazine on the special issue AI-eXplained (AI-X). The full paper includes interactive components to facilitate interested readers to grasp the idea of pure-strategy Nash equilibria and how the system

Reinforcement learning (RL) is a subset of machine learning that allows intelligent agents to acquire the ability of executing desired actions through interactions with an environment. Its remarkable progress has achieved significant results in diverse domains, such as Go and StarCraft, and practical challenges like protein-folding. This short paper presents overviews of two common RL approaches: the

Point cloud registration, which effectively coincides the source and target point clouds, is generally implemented by geometric metrics or feature metrics. In terms of resistance to noise and outliers, feature-metric registration has less error than the traditional point-to-point corresponding geometric metric, and point cloud reconstruction can generate and reveal more potential information during

The 7th Asian Conference on Artificial Intelligence Technology (ACAIT 2023)

Presents summaries of recent books published in the area of computational intelligence.

Evolutionary ensemble learning is an emerging research area, and designing an appropriate quality-diversity optimization algorithm to obtain a set of effective and complementary base learners is important. However, how to maintain such a set of learners remains an open issue. This paper proposes using cosine similarity-based dimensionality reduction methods to maintain a set of effective and complementary