7. Lasso, Ridge, and Elastic Net
We continue our discussion of ridge and lasso regression by focusing on the case of correlated features, which is a common occurrence in machine learning practice. We will see that ridge solutions tend to spread weight equally among highly correlated features, while lasso solutions may be unstable in the case of highly correlated features. Finally, we introduce the "elastic net", a combination of L1 and L2 regularization, which ameliorates the instability while maintaining some of the properties of lasso. (Credit to Brett Bernstein for the excellent graphics.) Access the full course at https://bloom.bg/2ui2T4q
▶︎
6. L1 & L2 Regularization
▶︎
8. Loss Functions for Regression and Classification
▶︎
Elastic Net Regularization : Data Science Concepts
▶︎
1. Black Box Machine Learning
▶︎
LASSO Regression in R (Part One)
▶︎
Ridge Regression Part 1 | Geometric Intuition and Code | Regularized Linear Models
▶︎
5. Excess Risk Decomposition
▶︎
20. Classification and Regression Trees
▶︎
Regularization Part 1: Ridge (L2) Regression
▶︎
Tutorial 27- Ridge and Lasso Regression Indepth Intuition- Data Science
▶︎
22. Bagging and Random Forests
▶︎
4. Stochastic Gradient Descent
▶︎
Elastic Net Regression in scikit-learn: Balancing L1 and L2 Optimizations
▶︎
12. Feature Extraction
▶︎
But what is a convolution?
▶︎
23. Gradient Boosting
▶︎
Ridge Regression
▶︎
The World's Most Important Machine
▶︎
Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM)
▶︎