Imagine using artificial intelligence to compare two seemingly unrelated creations: biological tissue and Beethoven’s “Symphony No. 9.” At first glance, a living system and a musical masterpiece may seem to have no connection. However, a new AI method developed by Markus J. Buehler, McAfee Professor of Engineering and professor of civil and environmental engineering and mechanical engineering at MIT, fills this gap, revealing common patterns of complexity and order.
“By combining generative AI with graph-based computing tools, this approach reveals entirely new ideas, concepts and designs that were previously unimaginable. We can accelerate scientific discovery by teaching generative AI to make new predictions about previously unseen ideas, concepts, and designs,” says Buehler.
Open access research, recently published in Machine learning: science and technologydemonstrates an advanced AI method that integrates generative knowledge extraction, graph-based representation, and multi-modal intelligent graph reasoning.
The work uses graphs developed using methods inspired by category theory as a central mechanism for teaching the model to understand symbolic relationships in science. Category theory, a branch of mathematics that deals with abstract structures and the relationships between them, provides a framework for understanding and unifying diverse systems by focusing on objects and their interactions, rather than their specific contents. In category theory, systems are considered in terms of objects (which can be anything from numbers to more abstract entities like structures or processes) and morphisms (arrows or functions that define the relationships between these objects). Using this approach, Buehler was able to teach the AI model to systematically reason about complex scientific concepts and behaviors. The symbolic relationships introduced by morphisms clearly show that AI is not just drawing analogies, but engaging in deeper reasoning that maps abstract structures across different domains.
Buehler used this new method to analyze a collection of 1,000 scientific articles on biological materials and transformed them into a knowledge map in the form of a graph. The graph revealed how different pieces of information are connected and helped find clusters of related ideas and key points that connect many concepts together.
“What’s really interesting is that the graph is scale-free, is highly connected, and can be used effectively for graphical reasoning,” says Buehler. “In other words, we teach AI systems to think about graph-based data to help them create better representational models of the world and improve their ability to think and explore new ideas to enable discovery.”
Researchers can use this framework to answer complex questions, find gaps in current knowledge, suggest new material designs, predict potential material behavior, and connect concepts that have never been connected before.
The AI model discovered unexpected similarities between biological materials and “Symphony No. 9,” suggesting that both follow patterns of complexity. “In the same way that cells in biological materials interact in a complex but organized way to perform a function, Beethoven’s 9th Symphony arranges musical notes and themes to create a complex but coherent musical experience,” says Buehler.
In another experiment, the graphics-based AI model recommended creating a new biological material inspired by the abstract patterns found in Wassily Kandinsky’s painting, “Composition VII.” AI suggested a new composite material based on mycelium. “The result of this material combines an innovative set of concepts that include a balance between chaos and order, tunable properties, porosity, mechanical strength and complexly patterned chemical functionality,” notes Buehler. Taking inspiration from an abstract painting, the AI created a material that balances its strength and functionality, while being adaptable and capable of fulfilling different roles. This application could lead to the development of innovative sustainable building materials, biodegradable alternatives to plastics, wearable technologies and even biomedical devices.
Using this advanced AI model, scientists can learn from music, art, and technology to analyze data from these fields to identify hidden patterns that could unlock a world of innovative possibilities for hardware design, research, and even music or visual arts.
“Graphics-based generative AI achieves a much higher degree of novelty, exploration of capabilities and technical details than conventional approaches, and establishes a broadly useful framework for innovation by revealing hidden connections,” says Buehler . “This study not only contributes to the field of bio-inspired materials and mechanics, but also paves the way for a future where interdisciplinary research powered by AI and knowledge graphs could become a tool for scientific and philosophical inquiry as we consider further future work. .”
