How primates recognize faces using AI-crafted face images

Revealing the mechanisms of primate face recognition with synthetic stimulus sets optimized to compare computational models

['FUNDING_R01'] · COLUMBIA UNIV NEW YORK MORNINGSIDE · NIH-10698908

This project uses AI-made face images to find how primate brains tell faces apart, aiming to help people who have trouble recognizing faces such as some people with autism.

Quick facts

Phase['FUNDING_R01']
Study typeNih_funding
SexAll
SponsorCOLUMBIA UNIV NEW YORK MORNINGSIDE (nih funded)
Locations1 site (NEW YORK, UNITED STATES)
Trial IDNIH-10698908 on ClinicalTrials.gov

What this research studies

The team builds computer neural networks that model how brains process faces and then uses optimization to create special 'controversial' face images that make the models give different answers. They will record brain responses in identified face-processing areas (using methods like fMRI and neurophysiology) to see which model predictions match real neural activity. By comparing model and brain responses to these targeted images, researchers hope to pin down the brain mechanisms that support face recognition. The work combines AI, brain imaging, and careful stimulus design to probe face processing more powerfully than standard image sets.

Who could benefit from this research

Good fit: Ideal candidates would include people with face-recognition difficulties (such as some individuals with autism or congenital prosopagnosia) as well as healthy volunteers who can participate in brain imaging or behavioral testing.

Not a fit: People whose health issues are unrelated to brain-based face recognition (for example, isolated eye disease or systemic conditions without cognitive effects) are unlikely to gain direct benefit.

Why it matters

Potential benefit: If successful, this work could improve understanding of why some people (for example, people with autism or prosopagnosia) struggle with face recognition and guide better diagnostic tests or targeted supports.

How similar studies have performed: Related studies have shown promising links between neural-network models and brain responses in face areas, but using optimized 'controversial' stimuli to force model disagreements is a more novel approach.

Where this research is happening

NEW YORK, UNITED STATES

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.

View on NIH RePORTER →

Conditions: Autistic Disorder, Beuren syndrome

Last reviewed 2026-05-15 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.