弹性反传神经网络法预测烷基苯的疏水性常数

Application of Resilient Backpropagation Neural Network in Predicting Hydrophobic Parameters of Alkylbenzenes

介绍了应用人工神经网络预测烷基苯分子疏水性常数的方法。该法同传统方法相比 ,具有操作简便 ,适用范围广的特点。基于误差反传神经网络 ,建立了分子连接性指数 (χ)、范德华表面积 (Aw)和疏水性常数 (logP)之间的数学模型。应用该模型对烷基苯分子的疏水性常数进行预测 ,其平均相对偏差为 0 6 7%。并且通过与标准误差反传算法和自适应学习算法相比较 ,发现弹性反传算法具有训练速度快 。

Artificial neural networks have been applied for predicting the hydrophobic parameters of alkylbenzene. Compared with traditional methods it has the advantages of simple operation and wide applications. Based on error back propagation neural networks the relationship among the molecular connectivity index ( χ ), van der Waals surface area ( A w) and hydrophobic parameter was studied, meanwhile the mathematical model was established and used to predict the hydrophobic parameters. By comparing the hydrophobic parameters of experimental values with those calculated by neural networks, we found they had good agreement. The average relative deviation was less than 1%. Because traditional back propagation network is generally time consuming, resilient backpropagation (RPROP) algorithm was used to solve this problem. By using RPROP algorithm, the hydrophobic parameters were obtained precisely by fast training and simple parameter's selection. It needed less than 1?000 iterations to reach the goal on the computer operated at 1 4 GHz. The present work shows that the artificial neural network is a new powerful tool to predict the physicochemical parameters.