Topic:
Incorporating Prior Function Belief into Neural Networks through Dropout and Negative Correlation Learning

keywords:
Dropout
Bayesian Approximation
Gaussian Process
Model Uncertainty
Negative Correlation Learning
generalization

Reference:
Srivastava, Nitish, et al. "Dropout: a simple way to prevent neural networks from overfitting." The journal of machine learning research 15.1 (2014): 1929-1958.
Gal, Y. & Ghahramani, Z. Dropout as a Bayesian approximation: representing model uncertainty in deep learning. Proc. Int. Conf. Mach. Learn. 48,1050–1059 (2016).
Liu, Y., & Yao, X. (1999). Ensemble learning via negative correlation. Neural networks, 12(10), 1399-1404.