Multiple Back-Propagation Algorithm

The Multiple Back-Propagation algorithm is a generalization of the Back-Propagation algorithm. Compared to the Back-Propagation algorithm Multiple Back-Propagation offers better generalization capabilities and faster training times.

For more information view this video. Alternatively you may read the following articles:

Noel Lopes and Bernardete Ribeiro. An efficient gradient-based learning algorithm applied to neural networks with selective actuation neurons. Neural, Parallel and Scientific Computations, 11:253{272, 2003.

Noel Lopes and Bernardete Ribeiro. Hybrid learning multi neural architecture. In INNS-IEEE International Joint Conference on Neural Networks (IJCNN 2001), volume 4, pages 2788-2793, 2001.