Machine Learning with Imbalanced Data is a training course on techniques to tackle data imbalance and improve the performance of your machine learning model. If you are currently working on unbalanced datasets and want to improve the performance of your model or you want to learn techniques that will help you deal with imbalanced data, then this course is for you.
We teach you step-by-step everything you need to work with unbalanced datasets with the help of fun educational videos. During this comprehensive course, we will teach all available methodologies for working with unbalanced datasets and discuss their rationale, how to use them in Python, and their advantages and disadvantages.
What you will learn in the Machine Learning with Imbalanced Data course:
- Random under-sampling methods
- “Undersampling” methods that focus on hard-to-classify observations.
- Low sampling methods to increase the number of minority observations
- Ways to construct dummy data to increase instances of the minority class
- SMOTE and its variables
- Using batch methods with sampling techniques to improve model efficiency
- The best evaluation criteria for use in unbalanced datasets
Instructors: Soledad Galli
Education level: Intermediate
Number of courses: 129
Duration: 11 hours and 541 minutes
Machine Learning with Imbalanced Data Course topics on 6/2022
Machine Learning with Imbalanced Data Course prerequisites:
After Extract, view with your favorite Player.
The version of 2022/3 compared to 2021/1 has increased the number of 25 lessons and the duration of 2 hours and 57 minutes.