back Back

AI finds cross-disciplinary connections and suggests research ideas

Nov. 19, 2024.
2 mins. read. 7 Interactions

AI finds connections between different scientific topics, offers insights, and suggests promising research ideas for further study.

About the Writer

Giulio Prisco

92.57456 MPXR

MIT scientists have developed a way for Artificial Intelligence (AI) to find connections between different scientific topics and suggest research ideas.

AI reproduces the results of human thought processes to a certain degree, but it usually struggles to link complex ideas from unrelated fields.

Generative AI can create new content, like text or music, by learning from existing data. The MIT scientists combined generative AI with graphs that show how things connect or relate to each other.

These graphs are based on category theory, a branch of abstract mathematics that models systems as collections of abstract objects and their relationships.

An open access paper published in Machine Learning: Science and Technology describes how the scientists made AI understand and reason about complex systems. The scientists trained AI systems with information from 1,000 scientific papers about biological materials, creating a map of knowledge.

An MIT press release summarizes some interesting connections found by the AI. An even more interesting one, analyzed in the paper, is found between flowers and nacre-inspired cement.

Microscopic view of nacre (Credit: Wikimedia Commons).
Microscopic view of nacre (Credit: Wikimedia Commons).

Nacre is an organic–inorganic composite material found in the inner shell of some mollusks. Nacre-inspired cement replicates some interesting properties of nacre in construction materials.

Creative research ideas

The scientists asked different large language models (LLM) to analyze multiple alternative paths between “a flower” and “nacre-inspired cement” in the knowledge graph. Then they asked the LLMs suggest creative research ideas.

The LLMs suggested creative research ideas indeed (see text boxes 1-4), with ChatGPT-4 showing “the most impressive reasoning capability and the most detailed response.”

All LLMs suggested to study the behavior of hydrogen and covalent bonds in certain materials. For examole, in chitosan (a natural polymer found in the exoskeleton of crustaceans) or polyethylene glycol dimethacrylate (PEGDMA).

GPT-4 also suggested to study how superhydrophobic surfaces, like those of rose petals, influence mechanical properties of materials.

This work shows that AI can help us think creatively across different fields, potentially leading to new discoveries.

Let us know your thoughts! Sign up for a Mindplex account now, join our Telegram, or follow us on Twitter

Comment on this article

2 Comments

2 thoughts on “AI finds cross-disciplinary connections and suggests research ideas

  1. Actually, AI reflects our thoughts. I mean, it represents how we think and our ways of thinking. If we train it in the wrong way, its outcomes will also be wrong. This means AI can evolve far beyond where it is now. The important thing is AI ethics. When we train AI on something, we should consider its impact on society and how others might use this innovation (e.g., for harmful activities)

    Like
    Dislike
    Share
    Reply
    1. I think this research means that AI (even the preliminary AI that we have now) does NOT merely reflect our thoughts when it is able to suggest research directions that nobody has thought of. Imagine (this is an example that I keep in mind when I think about these things) an AI that finds a cure for cancer by just spotting statistical regularities in a huge volume of disparate data. Wouldn't that be a new thought?

      Regarding harmful activities, I'll just paste what I replied to a comment to another post: Water can also be used in harmful ways (think of waterboarding). But a world without water wouldn't be a good place.


      Like
      Dislike
      Share
      Reply

4

Like

Dislike

Share

1

Comments
Reactions
💯 💘 😍 🎉 👏
🟨 😴 😡 🤮 💩

Here is where you pick your favorite article of the month. An article that collected the highest number of picks is dubbed "People's Choice". Our editors have their pick, and so do you. Read some of our other articles before you decide and click this button; you can only select one article every month.

People's Choice
Bookmarks