Every day, the world generates 328.77 million terabytes of data—enough to fill 1.5 trillion CDs—but most machine learning systems only look at simple, pairwise connections, missing the complex, higher-order relationships that actually govern biology, chemistry, and physics. This matters because real-world data is not a simple web of links. A protein’s function depends on its shape and multiple simultaneous interactions; a self-driving car’s 3D model must account for how surfaces, shadows, and textures relate to each other. Current deep learning, built on graphs that model only two-way connections, cannot capture these structures. The researcher will develop new mathematical representations called Unifying Complexes, which preserve the hierarchical nature of data while making higher-order relationships easier to work with, then build deep learning models that run natively on these representations. If successful, the work could improve 3D computer vision for safer autonomous vehicles, accelerate drug screening and repurposing by predicting protein-drug interactions more accurately, and model brain chemistry to aid Alzheimer’s research. The open-source software suite will also let other researchers and industries—from augmented reality to rare disease diagnostics—convert complex data into actionable insights without needing to rebuild the mathematics from scratch.
View original technical description
328.77 million terabytes of data are created each day. To put this in perspective, if you were to store all this data on CDs, you would need over 1.5 trillion CDs each day. Modern machine learning (ML), specifically deep learning (DL), works to interpret this massive data, uncover fascinating patterns, and make predictions. DL has been transformative in numerous areas, from healthcare and retail to finance and manufacturing. This rapid advancement, often led by large technology corporations, is evidenced by breakthroughs in conversational AI, like ChatGPT / GPT4, and text-guided image synthesis. Today, one in seven UK businesses have adopted at least one form of ML technology. Despite this success, a challenge lurks in the realm of modern ML. The data we collect from various sources tends to be unstructured and complex. For instance, our Facebook comments are influenced not only by our past conversations, mood, and thoughts but also by the intricate interplay between these factors. Similarly, the interaction between proteins depends on their shape and other interactions. To extract meaningful insights from data and solve real-world problems, we need to consider these complex 'higher-order relationships', which play a key role in areas such as creating accurate 3D models for safer self-driving cars, predicting drug-target interactions for effective drug repurposing during pandemics, and accurately modeling brain neurochemistry for developing life-saving medicine against Alzheimer's disease. Unfortunately, most current machine learning systems focus mainly on modeling pairwise connections and overlook these higher-order relationships. This limits their capability to represent and analyze complex data, especially acquired in scientific areas by X-ray scanners, electron microscopy, or 3D laser scanners. My fellowship aims to harness the potential of big data by developing a new paradigm of deep learning, which encompasses higher order relations at its core and considers the data topology - an important branch of mathematics studying the "shape of data". My proposed research will achieve this in three key objectives: (1) I will develop Unifying Complexes (UCs), novel data representations that simplify working with higher-order relationships while preserving the hierarchical nature of data. At present, the industry standard relies on graphs, which only model pairwise relationships. (2) Existing deep learning models won't readily adapt to the novel UCs I will be developing in Objective 1. I will therefore create a variety of deep learning models tailored to work natively with these UCs. From discriminative to generative, these models will enable learning from rich and complex data. (3) Lastly, I will deploy the UCs and the models developed in Objectives 1 and 2 to address a variety of challenges in multiple applications, including 3D computer vision, drug screening, discovery and design, and in building new and practically relevant theories of deep learning. Thanks to the resources and the uninterrupted time provided by Future Leaders Fellowship (FLF), as a result of UNTOLD, I will be delivering an open-source comprehensive software suite designed to harness the full potential of big, complex data. Beyond scientific dissemination, the widespread adoption of the DL models I develop as part of UNTOLD, will have substantial socioeconomic impacts such as improved augmented and virtual reality, safer self-driving cars, personalized medicine, and better understanding of rare diseases. This will both position the UK as a leader in cutting-edge ML research and will gradually enhance its presence across all sectors using ML to convert complex data into actionable insights.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know