用递归神经网络从猴脑信号预测运动，精度超现有方法。
Leveraging Recurrent Neural Networks for Predicting Motor Movements from Primate Motor Cortex Neural Recordings
- 用自编码门控循环单元模型提升解码泛化能力
- 在神经解码挑战中达0.71的R²得分，排名第一
- 模型剪枝减少41.4%计算量，性能几乎不变
本文提出一种高效的深度学习方法，用于从非人类灵长类动物运动皮层神经记录中解码运动行为。采用自编码门控循环单元（AEGRU）作为模型架构，自编码器仅在训练阶段使用以增强泛化能力。结合预处理技术，该模型在Neurobench基准上取得0.71的R²得分，超越基线模型，并在IEEE BioCAS 2024神经解码大赛中以R²排名首位。此外，通过模型剪枝使乘加操作（MAC）减少41.4%，同时保持与原模型相近的R²表现。
原文摘要 · Abstract (English)
This paper presents an efficient deep learning solution for decoding motor movements from neural recordings in non-human primates. An Autoencoder Gated Recurrent Unit (AEGRU) model was adopted as the model architecture for this task. The autoencoder is only used during the training stage to achieve better generalization. Together with the preprocessing techniques, our model achieved 0.71 $R^2$ score, surpassing the baseline models in Neurobench and is ranked first for $R^2$ in the IEEE BioCAS 2024 Grand Challenge on Neural Decoding. Model pruning is also applied leading to a reduction of 41.4% of the multiply-accumulate (MAC) operations with little change in the $R^2$ score compared to the unpruned model.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。