[Coursera | DL Specialization | 2 ] Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

https://www.coursera.org/learn/deep-neural-network

When training a neural network, you have to make a lot of decisions,such asthe number of layersthe number of hidden unitslearning ratesactivation func

You've learned previously that vectorization allows you to efficiently compute on all $m$ examples, that allows you to process your whole training set

Tuning Process

Batch normalization makes your hyperparameter search problem much easier,makes your neural network much more robust(튼튼한).And it will also enable you t

So far, the classification examples we've talked about have used binary calssification, where you had two possible labels, 0 or 1.What if we have mult

Today, there are many deep learning frameworks that makes it easy for you to implement neural networks.So rather than too strongly endorsing any of th

Adam papaer에서 Adam Optimization의 성능이 momentum보다 훨씬 빠른 속도로 수렴한다는 emirical performance를 보였다고 작성이 되어있는데,하지만 이는 경험적인 것이기 때문에 아무도 모른다보통 momentum이 default로