用神经微分方程建模蝾螈视网膜神经元，更高效且适合小数据场景。
Modeling Retinal Ganglion Cells with Neural Differential Equations
- 采用神经微分方程架构，提升建模效率与适应性。
- 相比CNN和LSTM，MAE更低、收敛更快、模型更小。
- 适合边缘部署，如视觉假体中的频繁重训练场景。
本研究探索了液态时恒网络（LTCs）和闭式连续时间网络（CfCs）在三种数据集上对虎蝾螈视网膜神经节细胞活动的建模能力。与卷积基线模型和LSTM相比，两种架构均实现了更低的平均绝对误差（MAE）、更快的收敛速度、更小的模型规模以及更优的查询时间，尽管皮尔逊相关系数略低。其高效性和可适应性使其特别适用于数据有限且需频繁重训练的场景，例如视觉假体中的边缘部署。
原文摘要 · Abstract (English)
This work explores Liquid Time-Constant Networks (LTCs) and Closed-form Continuous-time Networks (CfCs) for modeling retinal ganglion cell activity in tiger salamanders across three datasets. Compared to a convolutional baseline and an LSTM, both architectures achieved lower MAE, faster convergence, smaller model sizes, and favorable query times, though with slightly lower Pearson correlation. Their efficiency and adaptability make them well suited for scenarios with limited data and frequent retraining, such as edge deployments in vision prosthetics.
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。