Deep learning advances from GCC research institutions, including new architectures, training methods, and applied deep learning across healthcare, robotics, and language.
Researchers including Dr. Najwa Aaraj developed ML-FEED, a new exploit detection framework using pattern-based techniques. The model is 70x faster than LSTMs and 75,000x faster than Transformers in exploit detection tasks, while also being slightly more accurate. The "ML-FEED" paper won best paper at the 2022 IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications. Why it matters: This research enables more efficient real-time security applications and highlights growing AI expertise in the Arab world.
Researchers have developed a CNN-based deep learning model for predicting coastal flooding in cities under various sea-level rise scenarios. The model utilizes a vision-based, low-resource DL framework and is trained on datasets from Abu Dhabi and San Francisco. Results show a 20% reduction in mean absolute error compared to existing methods, demonstrating potential for scalable coastal flood management.
MBZUAI researchers developed a new deep learning method for rapid and accurate estimation of clinical measurements from echocardiograms. The method focuses on improving the measurement of the left ventricle ejection fraction, a key indicator of heart health. Their deep learning approach improves upon previous methods by better organizing data representation, enhancing performance and transferability. Why it matters: The AI-driven solution can potentially reduce analysis time for cardiologists, improve patient care, and be particularly beneficial in regions with limited healthcare resources.
MBZUAI and Sheikh Shakbout Medical City researchers developed PECon, a deep learning method for pulmonary embolism detection using CT scans and electronic health records. PECon uses neural networks and contrastive learning to encode and align image and text data. The method aims to improve diagnosis accuracy and speed, potentially saving lives. Why it matters: This research demonstrates AI's potential to enhance medical diagnostics in the UAE, addressing a critical healthcare challenge.
This paper explores the use of deep learning for anomaly detection in sports facilities, with the goal of optimizing energy management. The researchers propose a method using Deep Feedforward Neural Networks (DFNN) and threshold estimation techniques to identify anomalies and reduce false alarms. They tested their approach on an aquatic center dataset at Qatar University, achieving 94.33% accuracy and 92.92% F1-score. Why it matters: The research demonstrates the potential of AI to improve energy efficiency and operational effectiveness in sports facilities within the GCC region.
This paper introduces a deep learning framework for automated pain-level detection, designed for deployment in the UAE healthcare system. The system aims to assist in patient-centric pain management and diagnosis support, particularly relevant in situations with medical staff shortages. The research assesses the framework's performance using common approaches, indicating its potential for accurate pain level identification.
Abdullah Hamdi, a Ph.D. student at KAUST, is researching AI, deep learning, and computer vision in the Image and Video Understanding Lab under Associate Professor Bernard Ghanem. His work focuses on developing reliable testing methods for deep learning tools, particularly for sensitive applications like self-driving vehicles. Hamdi aims to disseminate AI knowledge and contribute to the AI ecosystem in the region. Why it matters: This highlights KAUST's role in fostering local AI talent and contributing to critical research areas like autonomous vehicles, aligning with Saudi Arabia's broader technology goals.
Researchers from Princeton University and Qatar Computing Research Institute (QCRI) are collaborating on artificial intelligence and deep learning projects. The partnership aims to leverage the expertise of both institutions to advance AI research. Specific project details or outcomes were not disclosed in the provided text. Why it matters: International collaborations of this nature can help foster innovation and knowledge transfer in the rapidly evolving field of AI.
KAUST Ph.D. student Adel Bibi is researching how to bridge the gap between theory and practice in deep learning, focusing on the mathematical understanding of deep learning models. Bibi is currently interning at Intel in Munich and previously worked on various computer vision problems. He aims to use optimization and mathematics to better understand deep learning models and build better models systematically from theory. Why it matters: This research contributes to the fundamental understanding of deep learning, potentially leading to more efficient and reliable AI systems developed in the region.
William Tang from Princeton spoke at KAUST about using deep learning to achieve nuclear fusion. Nuclear fusion, recreating stellar conditions on Earth, is considered the "holy grail" of power sources because it is clean and does not produce radioactive waste. Tokamaks, invented by Soviet physicists, are devices used to contain plasma, the superheated ionized gas required for fusion. Why it matters: KAUST is contributing to research on sustainable energy solutions, including exploring the potential of AI in nuclear fusion, a potentially transformative clean energy source.
Søren Brunak presented deep learning approaches for analyzing disease trajectories using data from 7-10 million patients in Denmark and the USA. The models predict future outcomes like mortality and specific diagnoses, such as pancreatic cancer, using 15-40 years of patient data. Disease trajectories and explainable AI can generate hypotheses for molecular-level investigations into causal aspects of disease progression. Why it matters: This research demonstrates the potential of large-scale patient data and AI to improve disease prediction and generate hypotheses for further investigation into disease mechanisms relevant to regional healthcare systems.
Shahar Harel, Head of AI at Quris, presented a BIO-AI approach to drug safety assessment using a 'patient-on-a-chip' platform. This platform simulates the human body and generates high-frequency microscopy and biochemical data on drug interactions, considering patient genomics and ethnicity. The data is used to train multimodal deep learning models to predict drug safety and provide patient-specific recommendations. Why it matters: This approach offers a potential alternative to animal models, promising faster and more personalized drug development while reducing safety concerns.
Pietro Liò from the University of Cambridge will discuss geometric deep learning techniques for building a digital patient twin using graph and hypergraph representation learning. The talk will focus on integrating Computational Biology and Deep Learning, considering physiological, clinical, and molecular variables. He will also cover explainable methodologies for clinicians and protein design using diffusion models. Why it matters: This highlights the growing interest in applying advanced AI techniques like geometric deep learning and diffusion models to healthcare challenges in the region, particularly for personalized medicine.
A Mixture of Experts (MoE) layer is a sparsely activated deep learning layer. It uses a router network to direct each token to one of the experts. Yuanzhi Li, an assistant professor at CMU and affiliated faculty at MBZUAI, researches deep learning theory and NLP. Why it matters: This highlights MBZUAI's engagement with cutting-edge deep learning research, specifically in efficient model design.
MBZUAI Assistant Professor Yuanzhi Li has been awarded a Sloan Research Fellowship in computer science by the Alfred P. Sloan Foundation. The fellowship recognizes early-career researchers for creativity, innovation, and research accomplishments. Li's research focuses on deep learning theory, including hierarchical feature learning in neural networks and optimization algorithms. Why it matters: This prestigious fellowship highlights MBZUAI's ability to attract and support high-caliber AI researchers, enhancing the institution's reputation and contributing to the growth of AI expertise in the UAE.
MBZUAI students and researchers presented findings at the Graduate Student Research Conference (GSRC) in Dubai, led by Assistant Professor Mohammad Yaqub. Topics included deep learning, computer learning, disease prediction, and AI in healthcare, with students from the BioMedIA lab presenting their work. Presentations covered areas like fetal ultrasound quality assessment, head and neck cancer diagnosis, and disease risk prediction using generative pre-trained transformers. Why it matters: This showcases MBZUAI's focus on applying AI to solve real-world healthcare problems and highlights the contributions of its students in advancing medical AI research.