Cortex Inspired Learning to Recover Damaged Signal Modality with ReD-SOM Model

TL;DR

This paper introduces ReD-SOM, a model inspired by the human brain's ability to recover lost data across modalities, combining neural networks and self-organizing maps to improve multimodal signal reconstruction.

Contribution

The paper presents a novel ReD-SOM model that simulates the McGurk Effect to recover damaged data modalities using a combination of VAEs, SOMs, and Hebb connections.

Findings

Enhanced signal reconstruction quality on multimodal datasets

Significant improvement in reconstructing distorted signals

Visual and quantitative evidence of the model's effectiveness

Abstract

Recent progress in the fields of AI and cognitive sciences opens up new challenges that were previously inaccessible to study. One of such modern tasks is recovering lost data of one modality by using the data from another one. A similar effect (called the McGurk Effect) has been found in the functioning of the human brain. Observing this effect, one modality of information interferes with another, changing its perception. In this paper, we propose a way to simulate such an effect and use it to reconstruct lost data modalities by combining Variational Auto-Encoders, Self-Organizing Maps, and Hebb connections in a unified ReD-SOM (Reentering Deep Self-organizing Map) model. We are inspired by human's capability to use different zones of the brain in different modalities, in case of having a lack of information in one of the modalities. This new approach not only improves the analysis of ambiguous data but also restores the intended signal! The results obtained on the multimodal dataset demonstrate an increase of quality of the signal reconstruction. The effect is remarkable both visually and quantitatively, specifically in presence of a significant degree of signal's distortion.