Systems and methods for regularizing neural networks

The disclosure generally relates to machine learning. More specifically, the disclosure relates to systems and methods for regularizing neural networks by decorrelating the neurons or other parametersof the neural networks during training of neural networks, thereby facilitating mutual innovation of the parameters. 本公开通常涉及机器学习。更具体地，本公开涉及通过在神经网络的训练期间解相关神经网络的神经元或其他参数来正则化神经网络的系统和方法，从而促进这些参数相互创新。