New blog post: "A Recipe for Training Neural Networks" https://karpathy.github.io/2019/04/25/recipe/ … a collection of attempted advice for training neural nets with a focus on how to structure that process over time
"init well." I've been trying to use learning rate finder techniques such as: https://towardsdatascience.com/estimating-optimal-learning-rate-for-a-deep-neural-network-ce32f2556ce0 …. I think the init well part was clearly a missing piece !
