L-M优化算法（trainlm）和贝叶斯正则化算法（trainbr）-LM optimization algorithm (trainlm) and Bayesian regularization algorithm (trainbr)

Software for Large-scale Bound-constrained or Unconstrained Optimization L-BFGS-B is a limited-memory quasi-Newton code for large-scale bound-constrained or unconstrained optimization. The code has been developed at th

基于梯度下降法的最优迭代算法，在深度学习和神经网络中应用非常广泛，也非常好用(The optimal iterative algorithm based on gradient descent method is widely used in depth learning and neural network, and it is also very useful.)