AI opens new era in cognitive studies of wild primates
Scientists created an AI system that uses facial recognition and real-time touchscreen testing to automate cognitive studies of capuchin monkeys in the wild. The American Journal of Primatology published a proof-of-concept for the novel method—dubbed CapuchinAI—developed by researchers at Emory University and Georgia Institute of Technology.
Scientists have developed a new AI system called CapuchinAI, which uses facial recognition and real-time touchscreen testing to evaluate the cognitive abilities of wild capuchin monkeys. This proof-of-concept, published in the American Journal of Primatology, aims to provide a scalable and systematic method for studying the cognitive abilities of primates in their natural environments.
Dr. Marcela Benítez, the lead researcher from Emory University, explains that primate cognition is rarely studied in the wild due to the difficulty of setting up experimental controls in unpredictable environments. The AI system addresses this challenge by integrating a compact, battery-powered computing platform into a field research setup, identifying individual capuchins with 97% accuracy, and delivering food rewards for correctly completed tasks.
The system has been tested successfully in the Taboga Forest Reserve of Costa Rica, demonstrating its potential for automating cognitive testing of wild primates and mapping individual differences across tasks. This innovative approach builds upon the legacy of Dr. Frans de Waal, who pioneered studies of animal cognition and emphasized treating primates as individuals.
The open-source nature of the paper allows other scientists to adapt the AI method for studying cognitive abilities across different species of wild primates in various environments.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
