# When and how to use a mix of loss functions for back-propagation?

I am trying to understand the best loss function to be used with a convolutional neural network. I came to know that we can mix two loss functions. Can any body share in what case was it done and how?

• In cases like regularization loss functions are mixed (although its not very effective in case of NN's). You can look into generative NNs like VAE's where 2 loss functions are mixed and used each with a different purpose. – DuttaA Oct 15 '19 at 12:22

loss1 = torch.nn.MSELoss(a,b)