This paper reports the findings from a longitudinal case study at University of York, UK. The findings from this study suggest that students and tutors in this programme employed different types and exhibited different degree of social presence when commu
J. Werfel, X. Xie, and H. Seung. In, MIT Press, (2003)Discussion of learning curves for stochastic gradient descent.
Besides gradient based approaches, the paper shortly describes (with additional references) weight perturbation and node perturbation approaches..