Institute of Computer Science, Academy of Sciences of the Czech Republic, Pod Vodárenskou Věží 2, 18207 Prague, Czech Republic.
Neural Netw. 2012 Sep;33:160-7. doi: 10.1016/j.neunet.2012.05.002. Epub 2012 May 22.
Integral transforms with kernels corresponding to computational units are exploited to derive estimates of network complexity. The estimates are obtained by combining tools from nonlinear approximation theory and functional analysis together with representations of functions in the form of infinite neural networks. The results are applied to perceptron networks.
利用核对应于计算单元的积分变换来推导出网络复杂度的估计。这些估计是通过将非线性逼近理论和泛函分析的工具与函数的无限神经网络表示形式相结合而得到的。所得结果应用于感知器网络。
