Emergence of Double-slit Interference by Representing Visual Space in Artificial Neural Networks

TL;DR

This paper demonstrates that convolutional neural networks can develop wave-like interference patterns, revealing interpretable mechanisms of visual space encoding similar to biological grid cells.

Contribution

It introduces a self-supervised CNN model that exhibits wave interference patterns, advancing understanding of visual space representation in artificial neural networks.

Findings

CNN exhibits double-slit interference patterns

Visual space encoding in CNN is interpretable

Periodic wave properties suggest a spatial metric role

Abstract

Artificial neural networks have realized incredible successes at image recognition, but the underlying mechanism of visual space representation remains a huge mystery. Grid cells (2014 Nobel Prize) in the entorhinal cortex support a periodic representation as a metric for coding space. Here, we develop a self-supervised convolutional neural network to perform visual space location, leading to the emergence of single-slit diffraction and double-slit interference patterns of waves. Our discoveries reveal the nature of CNN encoding visual space to a certain extent. CNN is no longer a black box in terms of visual spatial encoding, it is interpretable. Our findings indicate that the periodicity property of waves provides a space metric, suggesting a general role of spatial coordinate frame in artificial neural networks.