Neural Memory Decoding with EEG Data and Representation Learning

TL;DR

This paper presents a deep learning-based method for decoding memory from EEG data, achieving high accuracy in identifying recalled concepts and enabling neural information retrieval.

Contribution

It introduces a novel supervised contrastive learning approach for neural decoding from EEG, allowing identification of unseen concepts and application to information retrieval.

Findings

Average top-1 accuracy of 78.4% in concept identification

Method enables decoding of unseen concepts with reference data

Application demonstrated in neural information retrieval

Abstract

We describe a method for the neural decoding of memory from EEG data. Using this method, a concept being recalled can be identified from an EEG trace with an average top-1 accuracy of about 78.4% (chance 4%). The method employs deep representation learning with supervised contrastive loss to map an EEG recording of brain activity to a low-dimensional space. Because representation learning is used, concepts can be identified even if they do not appear in the training data set. However, reference EEG data must exist for each such concept. We also show an application of the method to the problem of information retrieval. In neural information retrieval, EEG data is captured while a user recalls the contents of a document, and a list of links to predicted documents is produced.