📚 Chapter 1:Practical Aspects of Deep Learning
In this chapter, you lear about Train / Dev / Test sets,Bias Variance,Basic Recipe for Machine Learning,Regularization,Why Regularization Reduces Overfitting?,Dropout Regularization,Other Regularization Methods,Normalizing Inputs,Vanishing-Exploding Gradients,Weight Initialization for Deep Networks,Numerical Approximation of Gradients,Gradient Checking
>Table of Content
- Train / Dev / Test sets|Video|Note|Slide|medium|
- Bias Variance|Video|Note|Slide|medium|
- Basic Recipe for Machine Learning|Video|Note|Slide|medium|
- Regularization|Video|Note|Slide|medium|
- Why Regularization Reduces Overfitting?|Video|Note|Slide|medium|
- Dropout Regularization|Video|Video1|Note|Slide|medium|
- Understanding Dropout|Video|Note|Slide|medium|
- Other Regularization Methods|Video|Note|Slide|medium|
- Normalizing Inputs|Video|Note|Slide|medium|
- Vanishing-Exploding Gradients|Video 2|Note|Slide|medium|
- Weight Initialization for Deep Networks|Video|Note|Slide|medium|
- Numerical Approximation of Gradients|Video|Note|Slide|medium|
- Gradient Checking|Video|Note|Slide|medium|
- Gradient Checking Implementation Notes|Video|Note|Slide|medium|