用格林函数展开递推法进行油藏优化计算
Unfolding recurrence by Green's functions for optimized reservoir computing
摘要:
皮层网络是强递归的,神经元具有内在的时间动力学。这使它们有别于深度前馈网络。尽管前馈网络的应用及其理论理解取得了巨大进展,但仍不清楚递归皮层网络中递归和非线性的相互作用如何有助于其功能。这项工作的目的是提出一个可解的经常性网络模型,链接到前馈网络。通过微扰方法,我们将时间连续的,经常性的动态转换成一个有效的前馈结构的线性和非线性的时间内核。由此产生的分析表达式,使我们能够建立最佳的时间序列分类随机水库网络。首先,这使得我们不仅可以优化读出矢量,还可以优化输入投影,从而展示出强大的潜在性能增益。其次,分析揭示了二阶刺激统计是如何与动态的非线性相互作用并提高性能的关键因素。
英文摘要:
Cortical networks are strongly recurrent, and neurons have intrinsic temporal dynamics. This sets them apart from deep feed-forward networks. Despite the tremendous progress in the application of feed-forward networks and their theoretical understanding, it remains unclear how the interplay of recurrence and non-linearities in recurrent cortical networks contributes to their function. The purpose of this work is to present a solvable recurrent network model that links to feed forward networks. By perturbative methods we transform the time-continuous, recurrent dynamics into an effective feed-forward structure of linear and non-linear temporal kernels. The resulting analytical expressions allow us to build optimal time-series classifiers from random reservoir networks. Firstly, this allows us to optimize not only the readout vectors, but also the input projection, demonstrating a strong potential performance gain. Secondly, the analysis exposes how the second order stimulus statistics is a crucial element that interacts with the non-linearity of the dynamics and boosts performance.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。