How to Make Deep Learning Models That Don’t Suck
blog.nanonets.com
How to Make Deep Learning Models That Don’t Suck
1–3 of 3 posts
Re: How to Make Deep Learning Models That Don’t Suck
#2Training deep learning models can be tough. They don't work without the right hyperparameters. The interactive blog gives an explanation of the algorithms that can automate the hyperparameter search and has all the code you need to try it out for yourself.
Re: How to Make Deep Learning Models That Don’t Suck
#3Great article! Might be worth adding that too much dropout can cause your model to never converge, which would be creating a model that "sucks!"