【文献阅读】Comparison of multi layer perceptron (MLP) and radial basis function (RBF) for construction cost estimation the case of turkey

（1）文章工作

In Turkey, the preliminary construction cost estimation is updated and published officially by “Unit Area Cost Method” (UACM). However, it’s known that the costs obtained through this method in which only construction area is taken into consideration have significant differences from actual costs.
The aim of this study is to compare the cost estimations obtained through “Multi-Layer Perceptron” (MLP) and “Radial Basis Function” (RBF), which are commonly used Artificial Neural Network (ANN) methods.
The results of MLP and RBF were also compared with the results of UACM and the validity of UACM was interpreted.
Consequently, estimated costs obtained from RBF were found to be higher than the actual costs with a 0.28% variance, while the estimated costs obtained from MLP were higher than actual values with a 1.11% variance. The approximate costs obtained from UACM are higher than actual costs with a 28.73% variance.
It was found that both ANN methods were showed better performance than the UACM but RBF was superior to MLP.

在土耳其，初步的建筑成本估算是由“单位面积成本法”(UACM)更新并正式公布的。但据了解，这种只考虑建筑面积的方法得到的成本与实际成本存在较大差异。
本研究的目的是比较通过“多层感知器”(MLP)和“径向基函数”(RBF)获得的成本估计，这是常用的人工神经网络(ANN)方法。
MLP和RBF的结果也与UACM的结果进行了比较，解释了UACM的有效性。
结果证明，RBF估算成本高于实际成本，方差为0.28%，而MLP估算成本高于实际成本，方差为1.11%。从UACM得到的近似成本高于实际成本，差异为28.73%。
结果表明，两种神经网络方法的性能都优于UACM方法，但RBF方法优于MLP方法。

（2）RBF相关

RBF network, which was initially used for multivariate interpolation problems, was developed for ANN applications in time and it has been used as an alternative MLP network.
A RBF network similarly consists of three layers; input layer, one hidden layer and output layer. However, between the input layer and hidden layer, a non-linear transformation which contains radial basis activation functions is utilized. A linear transformation is also utilized between the hidden layer and output layer.
RBF network uses a mixed strategy which contains unsupervised learning and, as well as, supervised learning. Supervised learning is performed for the linear
transformation, while unsupervised learning is performed for the non-linear transformation.
RBF network uses a non-iterative technique. In other words, RBF network is capable within the training data set. Therefore, RBF network is generally preferred for optimization studies.

最初用于多元插值问题的RBF网络，随着时间的发展被用于神经网络的应用，它已经被用作一种替代的MLP网络。
类似地，RBF网络由三层组成：输入层、隐藏层和输出层。但是，在输入层和隐层之间，存在利用包含径向基激活函数的非线性变换。在隐层和输出层之间也使用了线性变换。
RBF网络采用混合策略，其中包含无监督学习和有监督学习。监督学习是为线性变换，而非线性变换则进行无监督学习。
RBF网络采用非迭代技术。也就是说，RBF网络能够在训练数据集内进行。因此，RBF网络通常是优化研究的首选。
（迭代是 重复反馈 的动作，神经网络中我们希望通过迭代进行多次的训练以到达所需的目标或结果。）

MLP network has one or more hidden layer, while RBF network has only one hidden layer.
Neurons use logistic activation function in the hidden layer(s) for MLP network while they use radial basis activation function for RBF network.

MLP网络有一个或多个隐含层，而RBF网络只有一个隐含层。
MLP网络采用隐层logistic激活函数，RBF网络采用径向基激活函数。