ML from Scratch Logistic regression
- Data Cleanup: Encode features, Standardise features, etc.
This is necessary because the sigmoid function squashes really small and really large inputs.
- Weight Initialization
If the weight is too small it will bring you to the vanishing gradient problem if the weight is too large it will bring you to the exploding gradient problem. Instead, initialize the weight with a specific range.
This is necessary because the sigmoid function squashes really small and really large inputs.
- Weight Initialization
If the weight is too small it will bring you to the vanishing gradient problem if the weight is too large it will bring you to the exploding gradient problem. Instead, initialize the weight with a specific range.
qwertyboss
Author
Breaking the Weight initialization symmetry and why it matters: https://towardsdatascience.com/neural-network-breaking-the-symmetry-e04f963395dd
Please sign in to leave a comment.