1. Sutton, R.S., “Two Problems With Backpropagation and Other Steepest-Descent Learning Procedures for Networks”, Proc. 8th Annual Conf. of the Cognitive Science Society, 1986, pp 823–831.
2. “Learning Internal Representations by Error Propagation”;Rumelhart,1986
3. “An Adaptive Training Algorithm for Back Propagation Networks”;Chan;Computer Speech and Language,1987
4. “Accelerated Stochastic Approximation”;Kesten;Annals of Mathematical Statistics,1957
5. “Increased Rates of Convergence Through Learning Rate Adaptation”;Jacobs;Neural Networks,1988