[Tutorial][Choe] A recipe for training neural networks

Oct 29, 2021

Mostly for beginners, but this is a really good guideline.

https://karpathy.github.io/2019/04/25/recipe

I very much resonate with the very first tip:

“1. Become one with the data The first step to training a neural net is to not touch any neural net code at all and instead begin by thoroughly inspecting your data. This step is critical. I like to spend copious amount of time (measured in units of hours) scanning through thousands of examples, understanding their distribution and looking for patterns. Luckily, your brain is pretty good at this. “

In relation to this, see this 2-page AAAI student abstract for example:

Seung-Geon Lee, Jaedeok Kim, Hyun-Joo Jung, and Yoonsuck Choe. Comparing sample-wise learnability across deep neural network models. In Proceedings of the AAAI Conference on Artificial Intelligence (Student Abstract), volume 33, pages 9961-9962, 2019. https://ojs.aaai.org/index.php/AAAI/article/view/5117/4990

with 김재덕 Hyun-Joo Jung Seung-Geon Lee

← Back to all articles         Quick Navigation:    Next:[ j ] – Prev:[ k ] – List:[ l ]