Z2H Video 4, finished watching [Post #10, Day 24]

I have just finished watching Video 4 in the Z2H series. I talked about good initialization in my previous post. This video also introduced the concept of batch normalization, batch normalization layers sprinkled throughout an NN help to stabilize it. We finished the video by "PyTorch-ifying" the code we worked on in the first part of the video. I need to review this material for sure as a lot didn't sink in for me on this initial pass. I am wondering what the best way forward is from here, should I push on to the next video? Or should I start going back and reviewing previous material until I'm solid on every detail. I think I will certainly make a few passes through this Z2H series, each time understanding the concepts and details more deeply. I also need to work on the exercises to put my knowledge to the test.