Parallel Neural Network Learning Through Repetitive Bounded Depth Trajectory Branching

The neural network learning process is a sequence of network updates and can be represented b y sequence of points in the weight space that we call a learning trajectory. In this paper a new learning approach based on repetitive bounded depth trajectory branching M proposed. This approach has objectives of improving generalization and speeding up Convergence b y avoiding local minima when selecting an alternative trajectory. The ezperimental results show an improved generalization compared to the standard back-propagation learning algorithm. The proposed parallel implementation dramatically improves the algorithm eficiency to the level that computing time is not a critical factor in achieving improved generalization.