Yurii

did you try to modify `mu` and `mu_update_factor` values? did it help to solve your problem?

> Can you please tell me the ideal values for mu_update_factor and mu to avoid this error? Inversion happens on the jacobian matrix and the `mu` parameter is added to...

> But different combinations of mu_update_factor, mu and error threshold value are giving this same error. Sorry, maybe I misunderstood you, did you say that it worked for `mu_update_factor=1.1, mu=0.1...

Would it be possible for you to set `verbose=True` and share outputs that you're observing in the terminal ```python optimizer = algorithms.LevenbergMarquardt(network, signals=on_epoch_end, verbose=True) ```

@rdx10001 do you get the same error during the first training iteration or after some number of epochs?

@peterdekker thank you for reporting the problem. I wouldn't necessary say that this is a bug, but rather bad design on my part. It would be reproducible if during each...

That's a good point, I think I'll need to add this as a feature or at least mention it in the documentation. For now, you can do it like ```python...

you also need to remember that not every layer has weights (the`layer.weight` operation might fail) and some layers also can have `bias` (`layer.bias`) which you can also visualise with a...

Yes, it should be fixed in the 0.8.3 version, but I don't have time to finish it. Can you try installing neupy from this branch: https://github.com/itdxer/neupy/tree/v0.8.3 ?

Hi, as far as I know it will require rewriting some part of the code and I would like to wait a while (maybe a few months or half a...