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

Across the primate cortex, neurons that perform similar functions tend to be spatially grouped together. In the high-level visual cortex, this biological principle manifests itself as a modular organization of neuronal clusters, each tuned to a specific object category. 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 networks as test beds 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 (i.e. backpropagation of error). 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 small input perturbations, indicating an additional role for these connections in learning robust representations.