How Many Bytes Can You Take Out Of Brain-To-Text Decoding?

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Antonello, Richard, Sarma, Nihita, Tang, Jerry, Song, Jiaru, Huth, Alexander
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916257461174272
author Antonello, Richard
Sarma, Nihita
Tang, Jerry
Song, Jiaru
Huth, Alexander
author_facet Antonello, Richard
Sarma, Nihita
Tang, Jerry
Song, Jiaru
Huth, Alexander
contents Brain-computer interfaces have promising medical and scientific applications for aiding speech and studying the brain. In this work, we propose an information-based evaluation metric for brain-to-text decoders. Using this metric, we examine two methods to augment existing state-of-the-art continuous text decoders. We show that these methods, in concert, can improve brain decoding performance by upwards of 40% when compared to a baseline model. We further examine the informatic properties of brain-to-text decoders and show empirically that they have Zipfian power law dynamics. Finally, we provide an estimate for the idealized performance of an fMRI-based text decoder. We compare this idealized model to our current model, and use our information-based metric to quantify the main sources of decoding error. We conclude that a practical brain-to-text decoder is likely possible given further algorithmic improvements.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14055
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle How Many Bytes Can You Take Out Of Brain-To-Text Decoding?
Antonello, Richard
Sarma, Nihita
Tang, Jerry
Song, Jiaru
Huth, Alexander
Computation and Language
Artificial Intelligence
Emerging Technologies
Brain-computer interfaces have promising medical and scientific applications for aiding speech and studying the brain. In this work, we propose an information-based evaluation metric for brain-to-text decoders. Using this metric, we examine two methods to augment existing state-of-the-art continuous text decoders. We show that these methods, in concert, can improve brain decoding performance by upwards of 40% when compared to a baseline model. We further examine the informatic properties of brain-to-text decoders and show empirically that they have Zipfian power law dynamics. Finally, we provide an estimate for the idealized performance of an fMRI-based text decoder. We compare this idealized model to our current model, and use our information-based metric to quantify the main sources of decoding error. We conclude that a practical brain-to-text decoder is likely possible given further algorithmic improvements.
title How Many Bytes Can You Take Out Of Brain-To-Text Decoding?
topic Computation and Language
Artificial Intelligence
Emerging Technologies
url https://arxiv.org/abs/2405.14055