Castro Wilson, Oblitas Jimy, Santa-Cruz Roberto, Avila-George Himer
Facultad de Ingeniería, Universidad Privada del Norte, Cajamarca, Peru.
Centro de Investigaciones e Innovaciones de la Agroindustria Peruana, Amazonas, Peru.
PLoS One. 2017 Dec 13;12(12):e0189369. doi: 10.1371/journal.pone.0189369. eCollection 2017.
The objective of this research was to develop a methodology for optimizing multilayer-perceptron-type neural networks by evaluating the effects of three neural architecture parameters, namely, number of hidden layers (HL), neurons per hidden layer (NHL), and activation function type (AF), on the sum of squares error (SSE). The data for the study were obtained from quality parameters (physicochemical and microbiological) of milk samples. Architectures or combinations were organized in groups (G1, G2, and G3) generated upon interspersing one, two, and three layers. Within each group, the networks had three neurons in the input layer, six neurons in the output layer, three to twenty-seven NHL, and three AF (tan-sig, log-sig, and linear) types. The number of architectures was determined using three factorial-type experimental designs, which reached 63, 2 187, and 50 049 combinations for G1, G2 and G3, respectively. Using MATLAB 2015a, a logical sequence was designed and implemented for constructing, training, and evaluating multilayer-perceptron-type neural networks using parallel computing techniques. The results show that HL and NHL have a statistically relevant effect on SSE, and from two hidden layers, AF also has a significant effect; thus, both AF and NHL can be evaluated to determine the optimal combination per group. Moreover, in the three study groups, it is observed that there is an inverse relationship between the number of processors and the total optimization time.
本研究的目的是通过评估三个神经结构参数，即隐藏层数（HL）、每个隐藏层的神经元数（NHL）和激活函数类型（AF）对平方和误差（SSE）的影响，开发一种优化多层感知器型神经网络的方法。该研究的数据来自牛奶样本的质量参数（物理化学和微生物学参数）。架构或组合被组织成在穿插一、二和三层时生成的组（G1、G2和G3）。在每个组内，网络在输入层有三个神经元，在输出层有六个神经元，NHL为三到二十七个，AF有三种类型（正切Sigmoid函数、对数Sigmoid函数和线性函数）。架构的数量使用三种因子型实验设计确定，对于G1、G2和G3，分别达到63、2187和50049种组合。使用MATLAB 2015a，设计并实现了一个逻辑序列，用于使用并行计算技术构建、训练和评估多层感知器型神经网络。结果表明，HL和NHL对SSE有统计学上的相关影响，从两个隐藏层开始，AF也有显著影响；因此，可以评估AF和NHL以确定每组的最佳组合。此外，在三个研究组中，观察到处理器数量与总优化时间之间存在反比关系。
