Predicting Artificial Neural Network Representations to Learn Recognition Model for Music Identification from Brain Recordings

TL;DR

This paper presents a novel method for training music recognition models using EEG brain recordings by leveraging artificial neural network representations as supervisory signals, improving classification accuracy and advancing brain-computer interface research.

Contribution

It introduces a new approach that uses ANN representations to train recognition models from noisy EEG data, enhancing music identification accuracy.

Findings

Significant improvement in EEG-based music classification accuracy.

Demonstrated the effectiveness of using ANN representations as supervision.

Provides insights into the relationship between brain activity and ANN models.

Abstract

Recent studies have demonstrated that the representations of artificial neural networks (ANNs) can exhibit notable similarities to cortical representations when subjected to identical auditory sensory inputs. In these studies, the ability to predict cortical representations is probed by regressing from ANN representations to cortical representations. Building upon this concept, our approach reverses the direction of prediction: we utilize ANN representations as a supervisory signal to train recognition models using noisy brain recordings obtained through non-invasive measurements. Specifically, we focus on constructing a recognition model for music identification, where electroencephalography (EEG) brain recordings collected during music listening serve as input. By training an EEG recognition model to predict ANN representations-representations associated with music identification-we observed a substantial improvement in classification accuracy. This study introduces a novel approach to developing recognition models for brain recordings in response to external auditory stimuli. It holds promise for advancing brain-computer interfaces (BCI), neural decoding techniques, and our understanding of music cognition. Furthermore, it provides new insights into the relationship between auditory brain activity and ANN representations.