更改

== 变体 ==

== 变体 ==

=== 数据处理的群方法（Group method of data handling） ===

=== 数据处理的群方法（Group method of data handling） ===

数据处理的群方法(GMDH) <ref name="ivak1968">{{cite journal|year=1968|title=The group method of data handling – a rival of the method of stochastic approximation|url=|journal=Soviet Automatic Control|volume=13|issue=3|pages=43–55|last1=Ivakhnenko|first1=Alexey Grigorevich|authorlink=Alexey Grigorevich Ivakhnenko}}</ref> 突出了全自动结构和参数化模型优化。结点激活函数是允许加法和乘法操作的[https://en.wikipedia.org/wiki/Andrey_Kolmogorov Kolmogorov]-Gabor多项式。它使用八层的深度前馈多层感知机<ref name="ivak1971">{{Cite journal|last=Ivakhnenko|first=Alexey|date=1971|title=Polynomial theory of complex systems|url=|journal=IEEE Transactions on Systems, Man and Cybernetics (4)|issue=4|pages=364–378|pmid=|access-date=}}</ref> ，是一个逐层增长的[https://en.wikipedia.org/wiki/Supervised_learning 监督学习]网络，其中每层使用[https://en.wikipedia.org/wiki/Regression_analysis 回归分析]训练。使用验证集检测无用的项，通过[https://en.wikipedia.org/wiki/Regression_analysis 正则化]消除。结果网络的尺寸和深度取决于任务。<ref name="kondo2008">{{cite journal|last2=Ueno|first2=J.|date=|year=2008|title=Multi-layered GMDH-type neural network self-selecting optimum neural network architecture and its application to 3-dimensional medical image recognition of blood vessels|url=https://www.researchgate.net/publication/228402366_GMDH-Type_Neural_Network_Self-Selecting_Optimum_Neural_Network_Architecture_and_Its_Application_to_3-Dimensional_Medical_Image_Recognition_of_the_Lungs|journal=International Journal of Innovative Computing, Information and Control|volume=4|issue=1|pages=175–187|via=|last1=Kondo|first1=T.}}</ref>

数据处理的群方法(GMDH) <ref name="ivak1968">{{cite journal|year=1968|title=The group method of data handling – a rival of the method of stochastic approximation|url=|journal=Soviet Automatic Control|volume=13|issue=3|pages=43–55|last1=Ivakhnenko|first1=Alexey Grigorevich|authorlink=https://en.wikipedia.org/wiki/Alexey_Grigorevich_Ivakhnenko}}</ref> 突出了全自动结构和参数化模型优化。结点激活函数是允许加法和乘法操作的[https://en.wikipedia.org/wiki/Andrey_Kolmogorov Kolmogorov]-Gabor多项式。它使用八层的深度前馈多层感知机<ref name="ivak1971">{{Cite journal|last=Ivakhnenko|first=Alexey|date=1971|title=Polynomial theory of complex systems|url=|journal=IEEE Transactions on Systems, Man and Cybernetics (4)|issue=4|pages=364–378|access-date=}}</ref> ，是一个逐层增长的[https://en.wikipedia.org/wiki/Supervised_learning 监督学习]网络，其中每层使用[https://en.wikipedia.org/wiki/Regression_analysis 回归分析]训练。使用验证集检测无用的项，通过[https://en.wikipedia.org/wiki/Regression_analysis 正则化]消除。结果网络的尺寸和深度取决于任务。<ref name="kondo2008">{{cite journal|last2=Ueno|first2=J.|date=|year=2008|title=Multi-layered GMDH-type neural network self-selecting optimum neural network architecture and its application to 3-dimensional medical image recognition of blood vessels|url=https://www.researchgate.net/publication/228402366_GMDH-Type_Neural_Network_Self-Selecting_Optimum_Neural_Network_Architecture_and_Its_Application_to_3-Dimensional_Medical_Image_Recognition_of_the_Lungs|journal=International Journal of Innovative Computing, Information and Control|volume=4|issue=1|pages=175–187|via=|last1=Kondo|first1=T.}}</ref>

=== 卷积神经网络（Convolutional neural networks） ===

=== 卷积神经网络（Convolutional neural networks） ===