We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Predicting for Sustainable Insurance with Adaptive Gradient Methods.
- Authors
Sehgal, Parveen; Gupta, Sangeeta; Kumar, Dharminder
- Abstract
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.
- Subjects
ADAPTIVE computing systems; ARTIFICIAL neural networks; PREDICTION models; BACK propagation; COMPARATIVE studies
- Publication
BVICAM's International Journal of Information Technology, 2015, Vol 7, Issue 2, p896
- ISSN
0973-5658
- Publication type
Article