Researchers from the University of Glasgow’s School of Psychology and Neuroscience have developed a novel approach to understanding whether the human brain and its DNN models recognize things in the same way
Deep Neural Networks have become very significant in everyday real-world applications such as automated face recognition systems and self-driving cars. Deep Neural Network is used by researchers to model the processing of information and examine how this processing is equivalent to that of humans. While how DNNs perform computations can be very different from the human brain. Hence, researchers have invented a unique approach to understanding whether the human brain and its DNN models recognize things in the same way, using similar steps of computations.
Prof Philippe Schyns, Dean of Research Technology at the University of Glasgow, said: “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.
This article defines a new approach to better this understanding of how the process works: first, researchers must show that both the brain and the DNNs recognize the same things – such as a face – using the same face features; and, secondly, that the brain and the DNN must process these features in the same way, with the same steps of computations. This research would overcome the main hurdle in AI development i.e. understanding the process of machine learning, which matches how humans process information.
“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.”
This research would provide us with more accurate and reliable AI technology that will process information similar to the human brain
Click here for the Published Research Paper