The similarity between human and AI learning provides intuitive design insights

New research finds similarities between humans and artificial intelligence integrating two types of learning, providing new insights into how people learn and ways to develop more intuitive AI tools.

This study is published in Proceedings of the National Academy of Sciences.

Leading by Jake Rassin, a postdoctoral researcher in computer science at Brown University, the study was discovered by training AI systems that flexible, progressive learning modes interact with human working memory as well as long-term memory.

“These results help explain why humans appear to be rule-based learners in some situations, while in other situations they are progressive learners,” Rasin said. “They are also proposing something about what modern AI systems have in common with the human brain.”

Rasin is co-appointed by Michael Frank, professor of cognitive and psychological science and director of the Center for Computational and Brain Science at Brown's Kearney Institute of Brain Science, and Ellie Public, an associate professor of computer science, who leads the AI ​​Institute for AI Assistants in Brown.

Depending on the task, humans will retrieve new information in one of two ways. For some tasks, such as learning rules for TIC-TAC-Toe, learning “in-context” allows people to quickly grasp the rules after some examples. In other instances, incremental learning is based on information to improve understanding over time, such as the slow and sustained practices that come with learning to play songs on the piano.

Researchers knew that humans and AI would integrate both forms of learning, but it was not clear how the two learning types would work together. During the course of the research team's ongoing collaboration, Rasin, who bridges workbridge's machine learning and computational neuroscience, developed the theory that dynamics can resemble the interactions of human working and long-term memory.

To test this theory, Rasin used “metal learning.” This messes with the key properties of two learning types, using the types of training that helps the AI ​​system learn the learning itself. This experiment revealed that the ability of AI systems to perform in-context learning after meta-learning through multiple examples has emerged.

One experiment adapted from human experiments tested in-context learning by challenging AI to recombine similar ideas and deal with new situations. If I teach you about color lists and animal lists, can AI correctly identify combinations of colors and animals (such as green giraffes) that I have never seen before? After learning AI meta by challenging 12,000 similar tasks, we acquired the ability to successfully identify new combinations of colour and animal.

The results suggest that faster, flexible in-context learning occurs after a certain amount of progressive learning takes place in both humans and AI.

“In the first board game, it takes time to figure out how to play,” Public said. “By the time you learn the 100th board game, you'll quickly get the rules of play, even if you've never seen that particular game before.”

The team also discovered a trade-off between learning retention and flexibility. Like humans, the more difficult it is for AI to properly complete tasks, the more likely it is to remember how to execute them in the future. According to Frank, who studied this paradox in humans, this is because errors cued their brains to update information stored in long-term memory, whereas error-free actions learned in contexts increase flexibility, but do not involve long-term memory in the same way.

For Frank, who specializes in building biologically inspired computational models to understand human learning and decision-making, the team's work demonstrated how to provide new insights into the human brain by analyzing the pros and cons of various learning strategies in artificial neural networks.

“Our results are sure to hold together different aspects of human learning that neuroscientists have not previously grouped,” Frank said.

This work also suggests important considerations for developing intuitive and reliable AI tools, especially in sensitive domains such as mental health.

“To have a kind and reliable AI assistant, human and AI cognitions need to recognize how each function and the same range of things they do,” Pavlick said. “These discoveries are a great first step.”