Enhancing deep neural networks through complex-valued representations and Kuramoto synchronization dynamics

TL;DR

This paper explores how integrating complex-valued representations with Kuramoto synchronization dynamics can improve deep neural networks' ability to encode and distinguish multiple objects in visual scenes, inspired by neural synchrony in the brain.

Contribution

It introduces synchrony-based mechanisms combining complex-valued representations and Kuramoto dynamics into neural networks, enhancing multi-object encoding and robustness.

Findings

Models with synchrony outperform real-valued counterparts.

Synchronization improves robustness to noisy and overlapping inputs.

Enhanced generalization to out-of-distribution transformations.

Abstract

Neural synchrony is hypothesized to play a crucial role in how the brain organizes visual scenes into structured representations, enabling the robust encoding of multiple objects within a scene. However, current deep learning models often struggle with object binding, limiting their ability to represent multiple objects effectively. Inspired by neuroscience, we investigate whether synchrony-based mechanisms can enhance object encoding in artificial models trained for visual categorization. Specifically, we combine complex-valued representations with Kuramoto dynamics to promote phase alignment, facilitating the grouping of features belonging to the same object. We evaluate two architectures employing synchrony: a feedforward model and a recurrent model with feedback connections to refine phase synchronization using top-down information. Both models outperform their real-valued counterparts and complex-valued models without Kuramoto synchronization on tasks involving multi-object images, such as overlapping handwritten digits, noisy inputs, and out-of-distribution transformations. Our findings highlight the potential of synchrony-driven mechanisms to enhance deep learning models, improving their performance, robustness, and generalization in complex visual categorization tasks.