These are my notes taken during the course MITx 6.86x "Machine Learning with Python: From Linear Models to Deep Learning", in Sept-Dec 2021.
- Lecture 01. Introduction to Machine Learning
- Lecture 02. Linear Classifier and Perceptron
- Lecture 03. Hinge loss, Margin boundaries and Regularization
- Lecture 04. Linear Classification and Generalization
- Project 1: Automatic Review Analyzer
- Lecture 05. Linear Regression 9 of 9 possible points (9/9) 100%
- Lecture 06. Nonlinear Classification
- Lecture 07. Recommender Systems
Project 2: Digit recognition (part 1)
- Lecture 08. Introduction to Feedforward Neural Networks
- Lecture 09. Feedforward Neural Networks, Back Propagation, and Stochastic Gradient Descent (SGD)
- Lecture 10. Recurrent Neural Networks 1
- Lecture 11. Recurrent Neural Networks 2
- Lecture 12. Convolutional Neural Networks
Project 3: Digit recognition (part 2)
- Lecture 13. Clustering 1
- Lecture 14. Clustering 2
- Lecture 15. Generative Models
- Lecture 16. Mixture Models; EM algorithm
Project 4: Collaborative Filtering via Gaussian Mixtures
- Lecture 17. Reinforcement Learning 1
- Lecture 18. Reinforcement Learning 2
- Lecture 19: Applications: Natural Language Processing
Link: https://learning.edx.org/course/course-v1:MITx+6.86x+3T2021/home
Note: This repo includes code prepared by the course staff.
Note: Please inform me if I forgot to remove some answers to the graded problems.