Jan, 2024

[Re] 带有非线性和非高斯观测模型的贝叶斯滤波的判别式卡尔曼滤波器

TL;DRKalman filters are widely used for estimating hidden variables and their application in neural decoding is explored in this paper, presenting a new version that leverages Bayes' theorem for improved filter performance. The paper provides an open-source Python alternative to the authors' MATLAB algorithm, and the efficacy of the new filter is examined in neuroscientific contexts using multiple random seeds and previously unused trials from the authors' dataset.