更改
→计算能力(Computational power)
===计算能力(Computational power)===
===计算能力(Computational power)===
[https://en.wikipedia.org/wiki/Multilayer_perceptron 多层感知机]是一个通用函数逼近器, 被[https://en.wikipedia.org/wiki/Universal_approximation_theorem 通用逼近理论]证明。然而,考虑到所需神经元的数量,网络拓扑,权重和学习参数,证明是没有建设性的。
一种特殊的带有理值权(与全精度[https://en.wikipedia.org/wiki/Real_number 实数]值权相对)的循环结构具有一个[https://en.wikipedia.org/wiki/Universal_Turing_Machine 通用图灵机]<ref>{{Cite journal| title = Turing computability with neural nets | url = http://www.math.rutgers.edu/~sontag/FTPDIR/aml-turing.pdf | year = 1991 | journal = Appl. Math. Lett. | pages = 77–80 | volume = 4 | issue = 6 | last1 = Siegelmann | first1 = H.T. | last2 = Sontag | first2 = E.D. | doi = 10.1016/0893-9659(91)90080-F }}</ref> 的完整能力,通过使用有限数量的神经元和标准线性连接。另外,无理值权导致机器带有[https://en.wikipedia.org/wiki/Hypercomputation 超图灵]能力。<ref>{{cite journal |last1=Balcázar |first1=José |title=Computational Power of Neural Networks: A Kolmogorov Complexity Characterization |journal=Information Theory, IEEE Transactions on |date=Jul 1997 |volume=43 |issue=4 |pages=1175–1183 |doi=10.1109/18.605580 |url=http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=605580&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D605580 |accessdate=3 November 2014|citeseerx=10.1.1.411.7782 }}</ref>
===能力(Capacity)===
===能力(Capacity)===