# Training Neural Networks Good resources * [A Recipe for Training Neural Networks](https://karpathy.github.io/2019/04/25/recipe/) * [The Annotated Transformer](https://nlp.seas.harvard.edu/2018/04/03/attention.html) * [The Ultimate Training Loop](https://ankur-singh.github.io/blog/the-ultimate-training-loop) ### General Notes * In general you want the means of your activations to be near 0 and you want your standard deviations to be near 1 ([Lesson 16: Deep Learning Foundations to Stable Diffusion - YouTube](https://youtu.be/9YZaYjRKuEc?t=3662)) * --- Date: 20221002 Links to: Tags: #review References: * []()