# How can I access the weights at each training iteration of an MLP with scikit-learn?

I'm building an MLP with scikit-learn. Is there a way I can access the weights and biases of the output layer per iteration? There is an option mlp.coefs_, but it outputs the trained weights when the model is compiled. I need weights per iterations how can I get weights and biases per iteration?

You can use the MLP function partial_fit to perform a single training iteration at a time. If you do retrieve the weights between calls to this function, you can see what they look like after each iteration.