Online Handwritten Character Recognition Using an Optical Backpropagation Neural Networks

Citations Over TimeTop 20% of 2005 papers

Abstract

There are many successful applications of Backpropagation (BP) for training multilayer neural networks. However, they have many shortcomings. Learning often takes insupportable time to converge, and it may fall into local minima at all. One of the possible remedies to escape from local minima is using a very small learning rate, but this will slow the learning process. The proposed algorithm is presented for the training of multilayer neural networks with very small learning rate, especially when using large training set size. It can apply in a generic manner for any network size that uses a backpropgation algorithm through optical time. This paper studies the performance of the Optical Backpropagation algorithm OBP (Otair & Salameh, 2004a, 2004b. 2005) on training a neural network for online handwritten character recognition in comparison with backpropagation BP.

Related Papers

• → An improved backpropagation algorithm to avoid the local minima problem(2003)123 cited
• → Can backpropagation error surface not have local minima(1992)109 cited
• → Back propagation error surfaces can have local minima(1989)32 cited
• → Neural network training and stochastic global optimization(2004)2 cited
• → On the nonexistence of local minima of the backpropagation error surfaces(1991)1 cited