Sebastian Raschka

Thanks for highlighting this unintuitive behavior. It's definitely worth explaining with regard to left- and right-value. E.g., when we have ```python import numpy as np a = np.array([1, 2, 3,...

Hi, Andrew, thanks for the nice works and asking about the release date. Unfortunately, I don't have a release date in mind yet -- it's more like a "when it's...

Good question. Which notebook is that? My spontaneous thought is that I probably did that because PyTorch's data transformation normalizes pixels to [0, 1] range, and I wanted to have...

Usually gradient descent behaves a bit better if the values are centered at 0. (Ideally, the mean should be zero). In practice, I don't notice big differences though to be...

Yes, this happened to me to a couple of days ago. I think it's because the MNIST website is currently down: http://yann.lecun.com/exdb/mnist/ In your case `train_dataset = datasets.MNIST(root='data', ...)` will...

I think this is indeed a nice paper discussing the fact that in deep learning, it is (1) not only important to use fixed random seeds but (2) also to...

Here would be two. Before submitting, we need to make sure none of the co-authors is affiliated / friends with any of the reviewers we suggest. - Enrico Ferrero, https://scholar.google.com/citations?user=HAl-8xUAAAAJ&hl=en,...

Thanks for posting. Unless there are further suggestion, I suggest we keep the 4 researchers above as tentative reviewers to suggest. Everyone included in the author list would need to...

> I agree that class imbalance is a common issue in biology. How much of the discussion would be specific to deep learning as opposed to general ML? If the...

Hm, I agree that it's not really fitting into the context regarding DL recommendations for biologists, but it could fit into the intro as an example of interesting and challenging...