关于循环神经网络可控性的进一步结果
Further results on controllability of recurrent neural networks
摘要:
研究了循环神经网络的可控性。新的贡献是:(1)推广了“连续时间循环神经网络的完全可控性”一文的结果(Sontag和Sussmann)到一个略有不同的模型,其中输入出现在仿射形式,(2)制定和证明的充要条件,在局部局部可控性,和(3)在以前的工作中所作的假设不适用的二维情况下的完整分析
英文摘要:
This paper studies controllability properties of recurrent neural networks. The new contributions are: (1) an extension of the result in the previous paper "Complete controllability of continuous-time recurrent neural networks" (Sontag and Sussmann) to a slightly different model, where inputs appear in an affine form, (2) a formulation and proof of a necessary and sufficient condition, in terms of local-local controllability, and (3) a complete analysis of the 2-dimensional case for which the hypotheses made in previous work do not apply
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。