FBS Colloquia No.335Cognitive Neuroscience Group

Spontaneous segregation of visual information between parallel streams of a two-stream convolutional neural network

Visual information is processed in hierarchically organized parallel pathways in the primate brain. In lower cortical areas of the ventral stream, color information and shape information are processed in a parallel manner, while in higher cortical areas of the ventral stream, various types of visual information, such as color, face, animate/inanimate, are processed in a parallel manner. In the present study, the possibility of spontaneous segregation of visual information in parallel streams was examined by constructing a convolutional neural network with parallel architecture in all of the convolutional layers.
The results revealed that color information was segregated from shape information in most model instances. Deletion of the color-related stream decreased recognition accuracy in the inanimate category, whereas deletion of the shape-related stream decreased recognition accuracy in the animate category. The results suggest that properties of filters and functions of a stream are spontaneously segregated in parallel streams of neural networks.