Data Science: Decision Trees, Boosting and Ensembles
I'm Satyam ! I'm a Data Scientist at Gaana and an alumnus of BITS Pilani. This course is designed based on my experience in learning and working on Decision Trees and applying boosting and ensemble techniques.
I will start with basic concepts of decision trees and work with you on some real-world assignments. In the end, we’ll do some mock interviews to strengthen your ability to communicate what you’ve learnt.
- 15 live classes on data science concepts and live practice
- 1 Real world project
- Chat group to discuss and clear doubts
- Mentorship and interview preparation
I'm Satyam Kumar Singh. I'm a Data Scientist at Gaana and an alumnus of BITS Pilani.
What you'll learn
- Proficiency in all spheres of decision trees, random forests, boosting and ensembles techniques.
- Basic ML concepts like the bias-variance tradeoff along with detailed mathematical derivations.
- Grasp on decision trees for classification as well as regression for continuous and discrete features.
- Multi-label classification
- Understand bootstrapping and bagging, their difference and why bagging improves classification and regression performance.
- How to build Random Forests
- Adaboost and XGBoost ensemble techniques
- Apply all conecpts in a real world project
Class 1: Bias, variance and their derivation
Class 2-4: Building decision trees for classification and regression.
Class 5-9: Bootstrapping, Bagging
Class 8-10: Random Forest
Class 11: Boosting, AdaBoost
Class 12-13: XGBoost
Class 14-15: Mock interviews and Project review
Who should apply
Those who’ve started with the basics of Machine Learning and Python programming and want to get in-depth knowledge of Decision trees.
Slight exposure to Machine learning and basics of python programming
In a week, 2 hours in class and 4 hours outside class