文章基本信息

标题：Predicting for Sustainable Insurance with Adaptive Gradient Methods
本地全文：下载
作者：Parveen Sehgal ; Sangeeta Gupta ; Dharminder Kumar 等
期刊名称：BVICAM's International Journal of Information Technology
印刷版ISSN：0973-5658
出版年度：2015
卷号：7
期号：2
语种：English
出版社：Bharati Vidyapeeth's Institute of Computer Applications and Management
摘要：This paper extends the comparison of gradient based training methods used in the construction of prediction models based upon neural network, for sustainable insurance. Here adaptive gradient based techniques are compared with simple first order gradient based technique and with some second order training techniques for learning of the network. Convergence towards minimum error, for a number of first and second order algorithms are compared while utilizing data taken from live data warehouse of life insurance. Method of back propagation of errors is adopted for training of multilayer feed forward networks, while employing these gradient based algorithms of training error reduction. This paper is extended version of the paper presented in IEEE Conference INDIACom-2014.
关键词：Index Terms – Adaptive gradient algorithms;Error back propagation;Error gradient;Multilayer-perceptron;Neural network;Supervised training;Sustainable insurance.