Deep neural networks (DNNs)—part of the broader family of machine learning—have become increasingly powerful in everyday real-world applications such as automated face recognition systems and self-driving cars.
Researchers use DNNs to model the processing of information and to investigate how this information processing matches that of humans.
While DNNs have become an increasingly popular tool to model the computations that the brain does, particularly to visually recognize real-world “things,” the ways in which DNNs do this can be very different.
New research, published in the journal Trends in Cognitive Sciences and led by the University of Glasgow’s School of Psychology and Neuroscience, presents an approach to understand whether the human brain and its DNN models recognize things in the same way, using similar steps of computations.
A current challenge of accurate AI development is understanding whether the process of machine learning matches how humans process information. The researchers say they hope this new work will mark a step forward in the creation of more-accurate and -reliable AI technology that will process information more like our brains do.
“Having a better understanding of whether the human brain and its DNN models recognize things the same way would allow for more accurate real-world applications using DNNs,” said Philippe Schyns, the dean of research technology at the University of Glasgow.
“If we have a greater understanding of the mechanisms of recognition in human brains, we can then transfer that knowledge to DNNs, which, in turn, will help improve the way DNNs are used in applications such as facial recognition, where they are currently not always accurate,” he said. “Creating human-like AI is about more than mimicking human behavior. Technology must also be able to process information, or ‘think,’ like or better than humans if it is to be fully relied upon. We want to make sure AI models are using the same process to recognize things as a human would, so we don’t just have the illusion that the system is working.”
The study, Degrees of Algorithmic Equivalence Between the Brain and its DNN Models, is published in Trends in Cognitive Sciences.