The Geometry of Cortical Computation: Manifold Disentanglement and Predictive Dynamics in VCNet

TL;DR

This paper introduces VCNet, a neural network inspired by primate visual cortex, utilizing geometric principles to improve robustness and efficiency in visual tasks, outperforming existing models on specialized benchmarks.

Contribution

The paper presents VCNet, a biologically inspired geometric neural network architecture that incorporates hierarchical processing, disentangled representations, and predictive feedback, advancing the design of more robust AI models.

Findings

VCNet achieves 92.1% accuracy on Spots-10 dataset.

VCNet attains 74.4% accuracy on light field image classification.

VCNet surpasses comparable models in accuracy and robustness.

Abstract

Despite their success, modern convolutional neural networks (CNNs) exhibit fundamental limitations, including data inefficiency, poor out-of-distribution generalization, and vulnerability to adversarial perturbations. These shortcomings can be traced to a lack of inductive biases that reflect the inherent geometric structure of the visual world. The primate visual system, in contrast, demonstrates superior efficiency and robustness, suggesting that its architectural and computational principles,which evolved to internalize these structures,may offer a blueprint for more capable artificial vision. This paper introduces Visual Cortex Network (VCNet), a novel neural network architecture whose design is informed by the macro-scale organization of the primate visual cortex. VCNet is framed as a geometric framework that emulates key biological mechanisms, including hierarchical processing across distinct cortical areas, dual-stream information segregation for learning disentangled representations, and top-down predictive feedback for representation refinement. We interpret these mechanisms through the lens of geometry and dynamical systems, positing that they guide the learning of structured, low-dimensional neural manifolds. We evaluate VCNet on two specialized benchmarks: the Spots-10 animal pattern dataset, which probes sensitivity to natural textures, and a light field image classification task, which requires processing higher-dimensional visual data. Our results show that VCNet achieves state-of-the-art accuracy of 92.1\% on Spots-10 and 74.4\% on the light field dataset, surpassing contemporary models of comparable size. This work demonstrates that integrating high-level neuroscientific principles, viewed through a geometric lens, can lead to more efficient and robust models, providing a promising direction for addressing long-standing challenges in machine learning.