Predicting Artificial Neural Network Representations to Learn Recognition Model for Music Identification from Brain Recordings
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917875447496704 |
|---|---|
| author | Akama, Taketo Zhang, Zhuohao Li, Pengcheng Hongo, Kotaro Kitano, Hiroaki Minamikawa, Shun Polouliakh, Natalia |
| author_facet | Akama, Taketo Zhang, Zhuohao Li, Pengcheng Hongo, Kotaro Kitano, Hiroaki Minamikawa, Shun Polouliakh, Natalia |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_15560 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Predicting Artificial Neural Network Representations to Learn Recognition Model for Music Identification from Brain Recordings Akama, Taketo Zhang, Zhuohao Li, Pengcheng Hongo, Kotaro Kitano, Hiroaki Minamikawa, Shun Polouliakh, Natalia Neurons and Cognition Machine Learning Sound Audio and Speech Processing Signal Processing 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. |
| title | Predicting Artificial Neural Network Representations to Learn Recognition Model for Music Identification from Brain Recordings |
| topic | Neurons and Cognition Machine Learning Sound Audio and Speech Processing Signal Processing |
| url | https://arxiv.org/abs/2412.15560 |