Machine learning (ML) promises to revolutionize public health through improved surveillance, risk stratification, and resource allocation. However, without systematic attention to algorithmic bias, ML may inadvertently reinforce existing health disparities. We present a systematic literature review of algorithmic bias identification, discussion, and reporting in Dutch public health ML research from 2021 to 2025. To this end, we developed the Risk of Algorithmic Bias Assessment Tool (RABA T) by integrating elements from established frameworks (Cochrane Risk of Bias, PROBAST, Microsoft Responsible AI checklist) and applied it to 35 peer-reviewed studies. Our analysis reveals pervasive gaps: although data sampling and missing data practices are well documented, most studies omit explicit fairness framing, subgroup analyses, and transparent discussion of potential harms. In response, we introduce a four-stage fairness-oriented framework called ACAR (A wareness, Conceptualization, Application, Reporting), with guiding questions derived from our systematic literature review to help researchers address fairness across the ML lifecycle. We conclude with actionable recommendations for public health ML practitioners to consistently consider algorithmic bias and foster transparency, ensuring that algorithmic innovations advance health equity rather than undermine it.

The human brain receives nutrients and oxygen through an intricate network of blood vessels. Pathology affecting small vessels, at the mesoscopic scale, represents a critical vulnerability within the cerebral blood supply and can lead to severe conditions, such as Cerebral Small Vessel Diseases. The advent of 7 Tesla MRI systems has enabled the acquisition of higher spatial resolution images, making it possible to visualise such vessels in the brain. However, the lack of publicly available annotated datasets has impeded the development of robust, machine learning-driven segmentation algorithms. To address this, the SMILE-UHURA challenge was organised. This challenge, held in conjunction with the ISBI 2023, in Cartagena de Indias, Colombia, aimed to provide a platform for researchers working on related topics. The SMILE-UHURA challenge addresses the gap in publicly available annotated datasets by providing an annotated dataset of Time-of-Flight angiography acquired with 7T MRI. This dataset was created through a combination of automated pre-segmentation and extensive manual refinement. In this manuscript, sixteen submitted methods and two baseline methods are compared both quantitatively and qualitatively on two different datasets: held-out test MRAs from the same dataset as the training data (with labels kept secret) and a separate 7T ToF MRA dataset where both input volumes and labels are kept secret. The results demonstrate that most of the submitted deep learning methods, trained on the provided training dataset, achieved reliable segmentation performance. Dice scores reached up to 0.838 $\pm$ 0.066 and 0.716 $\pm$ 0.125 on the respective datasets, with an average performance of up to 0.804 $\pm$ 0.15.

Designing antennas in the wireless consumer electronic industry is a technical challenge that requires not only many efforts in simulation and measurement, but also experience in developing initial prototypes. The antenna space and the surrounding environment keep changing within various products. A well-designed antenna that meets the target of one product may not work with another even though they might come from the same production line. Selecting an initial antenna type, a monopole, loop or inverted F, to start with is critical. In many cases, it depends on who is the antenna engineer working on this project. For a same project and given the same specifications, different antenna engineers might surprisingly come out unalike types of antenna designs just because of their personalized experience and taste. In this era of rapid product iterations, there is high demand of creative antenna designs and it is hard to find antenna expertise. Therefore, in this paper, we will present a workflow of proposing good prototypes that antenna design experience is not a mandatory requirement. Antenna optimization have been widely studied and well presented in previous work, such as the trust region method Koziel and Unnsteinsson [2018], particle swarm method Jin and Rahmat-Samii [2007], evolutionary strategies Liu et al. [2014] and many types of machine learning methods Sharma et al. [2020], Koziel et al. [2021], Nan et al. [2021], This project is sponsored by Meta Internship Program.

Generative Artificial Intelligence (AI) is a cutting-edge technology capable of producing text, images, and various media content leveraging generative models and user prompts. Between 2022 and 2023, generative AI surged in popularity with a plethora of applications spanning from AI-powered movies to chatbots. In this paper, we delve into the potential of generative AI within the realm of the World Wide Web, specifically focusing on image generation. Web developers already harness generative AI to help crafting text and images, while Web browsers might use it in the future to locally generate images for tasks like repairing broken webpages, conserving bandwidth, and enhancing privacy. To explore this research area, we have developed WebDiffusion, a tool that allows to simulate a Web powered by stable diffusion, a popular text-to-image model, from both a client and server perspective. WebDiffusion further supports crowdsourcing of user opinions, which we use to evaluate the quality and accuracy of 409 AI-generated images sourced from 60 webpages. Our findings suggest that generative AI is already capable of producing pertinent and high-quality Web images, even without requiring Web designers to manually input prompts, just by leveraging contextual information available within the webpages. However, we acknowledge that direct in-browser image generation remains a challenge, as only highly powerful GPUs, such as the A40 and A100, can (partially) compete with classic image downloads. Nevertheless, this approach could be valuable for a subset of the images, for example when fixing broken webpages or handling highly private content.

The Arcade Learning Environment (ALE) has become an essential benchmark for assessing the performance of reinforcement learning algorithms. However, the computational cost of generating results on the entire 57-game dataset limits ALE's use and makes the reproducibility of many results infeasible. We propose a novel solution to this problem in the form of a principled methodology for selecting small but representative subsets of environments within a benchmark suite. We applied our method to identify a subset of five ALE games, called Atari-5, which produces 57-game median score estimates within 10% of their true values. Extending the subset to 10-games recovers 80% of the variance for log-scores for all games within the 57-game set. We show this level of compression is possible due to a high degree of correlation between many of the games in ALE.

In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge. Participants were tasked with developing a program or agent that can win (i.e., 'ascend' in) the popular dungeon-crawler game of NetHack by interacting with the NetHack Learning Environment (NLE), a scalable, procedurally generated, and challenging Gym environment for reinforcement learning (RL). The challenge showcased community-driven progress in AI with many diverse approaches significantly beating the previously best results on NetHack. Furthermore, it served as a direct comparison between neural (e.g., deep RL) and symbolic AI, as well as hybrid systems, demonstrating that on NetHack symbolic bots currently outperform deep RL by a large margin. Lastly, no agent got close to winning the game, illustrating NetHack's suitability as a long-term benchmark for AI research.

Rishabh Agarwal, Max Schwarzer, Pablo Samuel Castro, Aaron Courville and Marc G. Bellemare won an outstanding paper award at NeurIPS2021 for their paper Deep Reinforcement Learning at the Edge of the Statistical Precipice. In this blog post, Rishabh Agarwal and Pablo Samuel Castro explain this work. Reinforcement learning (RL) is an area of machine learning that focuses on learning from experiences to solve decision making tasks. While the field of RL has made great progress, resulting in impressive empirical results on complex tasks, such as playing video games, flying stratospheric balloons and designing hardware chips, it is becoming increasingly apparent that the current standards for empirical evaluation might give a false sense of fast scientific progress while slowing it down. To that end, in "Deep RL at the Edge of the Statistical Precipice", given as an oral presentation at NeurIPS 2021, we discuss how statistical uncertainty of results needs to be considered, especially when using only a few training runs, in order for evaluation in deep RL to be reliable.

The grand challenge of protein folding hit the news this week when it was announced that the latest version of DeepMind's AlphaFold system had predicted protein structures with very high accuracy in CASP's 2020 experiment. Proteins are large, complex molecules, and the shape of a particular protein is closely linked to the function it performs. The ability to accurately predict protein structures would enable scientists to gain a greater understanding of how they work and what they do. This new version of AlphaFold builds on the initial system, which you can read about in this paper. The associated code is available here.

Having risen to fame on its superhuman performance at playing games, the artificial intelligence group DeepMind has cracked a serious scientific problem that has stumped researchers for half a century. With its latest AI program, AlphaFold, the company and research laboratory showed it can predict how proteins fold into 3D shapes, a fiendishly complex process that is fundamental to understanding the biological machinery of life. Independent scientists said the breakthrough would help researchers tease apart the mechanisms that drive some diseases and pave the way for designer medicines, more nutritious crops and "green enzymes" that can break down plastic pollution. DeepMind said it had started work with a handful of scientific groups and would focus initially on malaria, sleeping sickness and leishmaniasis, a parasitic disease. "It marks an exciting moment for the field," said Demis Hassabis, DeepMind's founder and chief executive.