机译:A proof of convergence for gradient descent in the training of artificial neural networks for constant functions
Swiss Fed Inst Technol;
Univ Munster||Chinese Univ Hong Kong Shenzhen||Chinese Univ Hong Kong Shenzhen;
Swiss Fed Inst Technol||Univ Munster;
Artificial neural networks; Nonconvex optimization; Nonsmooth optimization; Gradient methods; Machine learning;