A new technique developed by mechanical and environmental engineering professor Markus J. Buehler will allow us to use artificial intelligence to predict how innovation will occur in the future.
Prof. Buehler of MIT explains that by combining graph-based computational tools with generative artificial intelligence, one can generate entirely new designs, concepts, and ideas. This, he notes, can be used to speed up scientific discovery by teaching generative artificial intelligence how to make new forecasts about unimaginable designs, concepts and ideas.
For his research, Buehler used graphs developed using techniques inspired by category theory to teach his model to understand associations in science.
Category theory is a mathematics branch that handles abstract structures and associations between them. It offers a framework for unifying and understanding different systems by focusing on objects and how they interact with other things. The artificial intelligence model was designed to uncover shared patterns of order and complexity.
In his research, the model discovered unanticipated similarities between Symphony No.9 by Beethoven and biological materials, proposing that both followed patterns of complexity. Through this approach, Buehler taught the model to methodically reason over different scientific behaviors and concepts.
In total, he analyzed one thousand scientific papers on biological materials and from the model, produced a graph which showed how different data was connected. The graph also showed groups of linked ideas and the points that linked different concepts.
Buehler explained that the graph followed a highly connected and scale-free nature which could be used for graph reasoning. He added that investigators could use the model to connect concepts that had never been linked before, suggest new material designs, answer difficult questions, find gaps in knowledge, and forecast how materials may behave.
For instance, the model could be used to develop biodegradable plastic alternatives, and innovative sustainable construction materials. In a separate experiment, the model recommended the creation of a new biological material based on the abstract patterns in Composition VII by Wassily Kandinsky.
With this advanced artificial intelligence model, researchers can draw insights from technology, art, and music to point out hidden patterns that could open up new possibilities for visual art, music, and material design.
Irving Langmuir Distinguished Professor of Chemical Sciences and Engineering, Nicholas Kotov, explained that graphs from Buehler’s work could be used as data maps that allowed researchers to identify new links, main topics, and possible research directions by exploring associations across subsections of biomimetic and bioinspired materials. Kotov was not involved in this study.
Buehler’s research was published in Machine Learning: Science and Technology.
As more AI innovations are brought to market by entities like C3.ai Inc. (NYSE: AI), a lot more use cases for this technology are likely to be uncovered leveraging the pattern recognition powers that Buehler’s study highlights.
About AINewsWire
AINewsWire (“AINW”) is a specialized communications platform with a focus on the latest advancements in artificial intelligence (“AI”), including the technologies, trends and trailblazers driving innovation forward. It is one of 70+ brands within the Dynamic Brand Portfolio @ IBN that delivers: (1) access to a vast network of wire solutions via InvestorWire to efficiently and effectively reach a myriad of target markets, demographics and diverse industries; (2) article and editorial syndication to 5,000+ outlets; (3) enhanced press release enhancement to ensure maximum impact; (4) social media distribution via IBN to millions of social media followers; and (5) a full array of tailored corporate communications solutions. With broad reach and a seasoned team of contributing journalists and writers, AINW is uniquely positioned to best serve private and public companies that want to reach a wide audience of investors, influencers, consumers, journalists, and the general public. By cutting through the overload of information in today’s market, AINW brings its clients unparalleled recognition and brand awareness.
AINW is where breaking news, insightful content and actionable information converge.
To receive SMS alerts from AINewsWire, text “AI” to 888-902-4192 (U.S. Mobile Phones Only)
For more information, please visit www.AINewsWire.com
Please see full terms of use and disclaimers on the AINewsWire website applicable to all content provided by AINW, wherever published or re-published: https://www.AINewsWire.com/Disclaimer
AINewsWire
Los Angeles, CA
www.AINewsWire.com
310.299.1717 Office
Editor@AINewsWire.com
AINewsWire is powered by IBN