# Predicting artificial neural network representations to learn recognition model for music identification from brain recordings

## TL;DR

This paper introduces a new method for identifying music from brain recordings by using artificial neural network representations as a guide, improving recognition accuracy and offering insights into brain activity and music cognition.

## Contribution

The novel approach uses ANN representations as a supervisory signal to train models on noisy brain recordings for music identification.

## Key findings

- Training EEG models to predict ANN representations significantly improves music identification accuracy.
- The method provides new insights into the relationship between auditory brain activity and artificial neural network representations.

## 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 significant 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.