This paper introduces an explainable machine learning framework for early-stage chronic kidney disease (CKD) screening, specifically designed for low-resource settings in Bangladesh and South Asia. The framework utilizes a community-based dataset from Bangladesh and evaluates multiple ML classifiers with feature selection techniques. Results show that the ML models achieve high accuracy and sensitivity, outperforming existing screening tools and demonstrating strong generalizability across independent datasets from India, the UAE, and Bangladesh.
This paper introduces Provable Unrestricted Adversarial Training (PUAT), a novel adversarial training approach. PUAT enhances robustness against both unrestricted and restricted adversarial examples while improving standard generalizability by aligning the distributions of adversarial examples, natural data, and the classifier's learned distribution. The approach uses partially labeled data and an augmented triple-GAN to generate effective unrestricted adversarial examples, demonstrating superior performance on benchmarks.
MBZUAI welcomed 45 international STEM students to its month-long Undergraduate Research Internship Program (UGRIP), a 32% increase from its second year. The program exposes students to AI research and faculty, attracting applicants from universities like IIT Madras, Harvard, and Yale. Interns worked on AI projects including digital healthcare metaverse prototypes, baby cry analysis, and LLM generalizability. Why it matters: This program helps to foster AI talent and promote the UAE as a global hub for AI research.
MBZUAI researchers have developed a new approach to enhance the generalizability of vision-language models when processing out-of-distribution data. The study, led by Sheng Zhang and involving multiple MBZUAI professors and researchers, addresses the challenge of AI applications needing to manage unforeseen circumstances. The new method aims to improve how these models, which combine natural language processing and computer vision, handle new information not used during training. Why it matters: Improving the adaptability of vision-language models is critical for real-world AI applications like autonomous driving and medical imaging, especially in diverse and changing environments.
Dr. Mohammad Yaqub from MBZUAI will present AI solutions used to combat the COVID-19 pandemic, addressing healthcare consequences, social, economic, and policy-making decisions. The talk will cover the applications of AI and also discuss challenges like privacy, data needs, generalizability, data noise, and human acceptance. Yaqub's background includes a DPhil from the University of Oxford in Biomedical Engineering and research at the Institute of Biomedical Engineering, focusing on machine learning solutions for medical problems. Why it matters: This talk highlights the important role of AI in addressing pandemics and the ethical considerations that come with its application in healthcare and policymaking.