AI Incorporates Cognitive Processes Typical of People with Autism

Vanderbilt University has been working to create an artificial intelligence (AI) system that incorporates the cognitive processes of people with autism into the code. The research informs both development of a robust AI and enhanced understanding of the cognitive processes of people on the autism spectrum. The system replicates models of human cognition and is trained to solve many cognitive tests to improve its problem-solving abilities. Assistant Professor of Computer Science Maithilee Kunda said, “One of the big mysteries we have right now is there is so much variability among different people on the spectrum and how they think. By trying to pin down these visual reasoning processes more carefully, we’re hoping we can start to divide up that spectrum into people who reason in particular ways and support them more effectively.”

 

The AI can be useful to autism studies as it learns and refines its tools that are not neurotypical, and therefore draw from varied sources to achieve the task. Reflecting on the problem-solving capabilities of the AI, Kunda said, “Most of us think in a combination of lots of different things. We think in words, we think in pictures, we think in smells and feelings. What we see in some people with autism is that they’re very much on the visual side.”