Local lateral connectivity is sufficient for replicating cortex-like topographical organization in deep neural networks

Abstract

Across the primate cortex, neurons that perform similar functions tend to be spatially grouped together. This biological principle extends to many other species as well, reflecting a common way of organizing sensory processing across diverse forms of life. In the visual cortex, this biological principle manifests itself as a modular organization of neuronal clusters, each tuned to a specific visual property. The tendency toward short connections is widely believed to explain the existence of such an organization in the brains of many animals. However, the neural mechanisms underlying this phenomenon remain unclear. Here, we use artificial deep neural network models to demonstrate that a topographical organization akin to that in the primary, intermediate, and high-level human visual cortex emerges when units in these models are locally laterally connected and their weight parameters are tuned by top-down credit assignment. The emergence of modular organization without explicit topography-inducing learning rules or objective functions challenges their necessity and suggests that local lateral connectivity alone may suffice for the formation of topographic organization across the cortex. Furthermore, the incorporation of lateral connections in deep convolutional networks enhances their robustness to subtle alterations in visual inputs, such as those designed to deceive the model (i.e. adversarial examples), indicating an additional role for these connections in learning robust representations.