Improving the Convergence Property of Soft Committee Machines by Replacing Derivative with Truncated Gaussian Function
暂无分享,去创建一个
[1] M. Rattray,et al. Incorporating curvature information into on-line learning , 1999 .
[2] Michael Biehl,et al. Learning by on-line gradient descent , 1995 .
[3] Kenji Fukumizu,et al. Adaptive Method of Realizing Natural Gradient Learning for Multilayer Perceptrons , 2000, Neural Computation.
[4] Saad,et al. On-line learning in soft committee machines. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.
[5] Masato Okada,et al. Theoretical Analysis of Function of Derivative Term in On-Line Gradient Descent Learning , 2012, ICANN.
[6] Yee Whye Teh,et al. A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.