Fig. 1: Architecture of number deep neural network (nDNN) adapted from the biologically-inspired CORnet-S. | Nature Communications

Fig. 1: Architecture of number deep neural network (nDNN) adapted from the biologically-inspired CORnet-S.

From: Learning-induced reorganization of number neurons and emergence of numerical representations in a biologically inspired neural network

Fig. 1: Architecture of number deep neural network (nDNN) adapted from the biologically-inspired CORnet-S.The alternative text for this image may have been generated using AI.

nDNN consists of four layers that model hierarchy and recurrent circuit dynamics in areas V1, V2, V3, and IPS of the dorsal visual processing stream. The architecture of nDNN is adapted from CORnet-S, a biologically inspired network architecture for visual object categorization. The nDNN is trained to map non-symbolic representation of numbers to their symbolic representation. The nDNN includes feedforward and recurrent (shown by looped arrows within a layer in the figure) connections.

Back to article page