NeuroSketch: An Effective Framework for Neural Decoding via Systematic Architectural Optimization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909954679504896 |
|---|---|
| author | Zhang, Gaorui Yuan, Zhizhang Yang, Jialan Chen, Junru Meng, Li Yang, Yang |
| author_facet | Zhang, Gaorui Yuan, Zhizhang Yang, Jialan Chen, Junru Meng, Li Yang, Yang |
| contents | Neural decoding, a critical component of Brain-Computer Interface (BCI), has recently attracted increasing research interest. Previous research has focused on leveraging signal processing and deep learning methods to enhance neural decoding performance. However, the in-depth exploration of model architectures remains underexplored, despite its proven effectiveness in other tasks such as energy forecasting and image classification. In this study, we propose NeuroSketch, an effective framework for neural decoding via systematic architecture optimization. Starting with the basic architecture study, we find that CNN-2D outperforms other architectures in neural decoding tasks and explore its effectiveness from temporal and spatial perspectives. Building on this, we optimize the architecture from macro- to micro-level, achieving improvements in performance at each step. The exploration process and model validations take over 5,000 experiments spanning three distinct modalities (visual, auditory, and speech), three types of brain signals (EEG, SEEG, and ECoG), and eight diverse decoding tasks. Experimental results indicate that NeuroSketch achieves state-of-the-art (SOTA) performance across all evaluated datasets, positioning it as a powerful tool for neural decoding. Our code and scripts are available at https://github.com/Galaxy-Dawn/NeuroSketch. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09524 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NeuroSketch: An Effective Framework for Neural Decoding via Systematic Architectural Optimization Zhang, Gaorui Yuan, Zhizhang Yang, Jialan Chen, Junru Meng, Li Yang, Yang Neurons and Cognition Artificial Intelligence Machine Learning Signal Processing Neural decoding, a critical component of Brain-Computer Interface (BCI), has recently attracted increasing research interest. Previous research has focused on leveraging signal processing and deep learning methods to enhance neural decoding performance. However, the in-depth exploration of model architectures remains underexplored, despite its proven effectiveness in other tasks such as energy forecasting and image classification. In this study, we propose NeuroSketch, an effective framework for neural decoding via systematic architecture optimization. Starting with the basic architecture study, we find that CNN-2D outperforms other architectures in neural decoding tasks and explore its effectiveness from temporal and spatial perspectives. Building on this, we optimize the architecture from macro- to micro-level, achieving improvements in performance at each step. The exploration process and model validations take over 5,000 experiments spanning three distinct modalities (visual, auditory, and speech), three types of brain signals (EEG, SEEG, and ECoG), and eight diverse decoding tasks. Experimental results indicate that NeuroSketch achieves state-of-the-art (SOTA) performance across all evaluated datasets, positioning it as a powerful tool for neural decoding. Our code and scripts are available at https://github.com/Galaxy-Dawn/NeuroSketch. |
| title | NeuroSketch: An Effective Framework for Neural Decoding via Systematic Architectural Optimization |
| topic | Neurons and Cognition Artificial Intelligence Machine Learning Signal Processing |
| url | https://arxiv.org/abs/2512.09524 |