Cortex Inspired Learning to Recover Damaged Signal Modality by ReD-SOM Model
Résumé
Recent progress in the fields of AI and cognitive sciences opens up new challenges and problems 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 reproduce 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 show 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.
Mots clés
Self-organizing feature maps
Analytical models
Technological innovation
Biological system modeling
Brain modeling
Distortion
Data models
Bio-inspired learning
Self-organizing Maps
Variational Auto-encoder
Hebb's connections
Data reconstruction
Deep learning
Unsupervised Learning
Multimodal association
brain
cognition
learning (artificial intelligence)
self-organising feature maps
signal reconstruction