arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1409.0280cs.NE
收藏

回声状态网络的一种演算

Towards a Calculus of Echo State Networks

Alireza Goudarzi, Darko Stefanovic

摘要:

储备池计算是神经网络中的一个新趋势,它利用系统相空间上的动态扰动来计算期望的目标函数。我们提出了如何制定一个简单的一类称为回声状态网络的储备池计算的系统性能的期望。与以前的理论框架,它只揭示了在系统中的总内存的上限相比,我们分析计算整个内存曲线作为系统的结构和输入和目标函数的属性的函数。我们证明了我们的框架的精度,通过验证其结果为广泛的系统尺寸和光谱半径。我们的分析计算与数值模拟一致。据我们所知,这项工作提出了第一个确切的分析特性的记忆曲线的回声状态网络。

英文摘要:

Reservoir computing is a recent trend in neural networks which uses the dynamical perturbations on the phase space of a system to compute a desired target function. We present how one can formulate an expectation of system performance in a simple class of reservoir computing called echo state networks. In contrast with previous theoretical frameworks, which only reveal an upper bound on the total memory in the system, we analytically calculate the entire memory curve as a function of the structure of the system and the properties of the input and the target function. We demonstrate the precision of our framework by validating its result for a wide range of system sizes and spectral radii. Our analytical calculation agrees with numerical simulations. To the best of our knowledge this work presents the first exact analytical characterization of the memory curve in echo state networks.

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。

↑