Neural Networks

Researchers from The University of Osaka have revealed that vision transformers can develop gaze patterns similar to humans, learning to prioritize faces without ever being taught what a face is. The findings suggest that self-supervised ViTs may serve as a practical tool in computer vision and a theoretical model for studying human visual processing. The research underscores the potential of biologically inspired AI systems to uncover the mechanisms of human cognition.

How do Directional Connections Shape Complex Dynamics in Neuronal Networks?

- The developed image translation model can yield accurate classification results despite the use of biased data for the training of a deep learning model. - This solution is expected to be applied in various fields, such as self-driving, content creation, and medicine.