Abstract
Artificial Neural Networks (ANNs) can fit non-linear functions and recognize patterns better than several standard techniques. Performance of ANNs is measured by using loss functions. Phi-divergence estimator is generalization of maximum likelihood estimator and it possesses all its properties. A neural network is proposed which is trained using phi-divergence loss.
DOI
10.22237/jmasm/1551966252
Recommended Citation
Salamwade, R. L., Sakate, D. M., & Mathur, S. K. (2018). ϕ-divergence loss-based artificial neural network. Journal of Modern Applied Statistical Methods, 17(2), eP2646. doi: 10.22237/jmasm/1551966252
Included in
Applied Statistics Commons, Social and Behavioral Sciences Commons, Statistical Theory Commons
