BP neural Network--using L2 for regularization

Through this article, we will see that in the original framework, neural network Topology (topology), computational flow (back propagation) based on the addition of new mathematical tools, to improve, do not need to the framework of the basic structure of the big move, just a small fine-tuning, so, Applying the new mathematical mechanism to the original network structure, the computational framework does not have to be formidable enemy, as we have seen before: BP neural network--from two cost functions (quadratic costs) to the cost function of the cross entropy (cross-entropy costing), BP neural Network-- How to initialize a weighted value.