Parallel neural learning by iteratively adjusting error thresholds

We first propose a modified backpropagation learning algorithm that incrementally decreases the error threshold by half in order to process training instances with large weight changes as quickly as possible. This modified backpropagation learning algorithm is then parallelized using the single-channel broadcast communication model to n processors, where n is the number of training instances. Finally, the parallel backpropagation learning algorithm is modified for execution on a bounded number of processors to cope with real-world conditions