Here is some short notes I am preparing for this course. It will be useful for revision.
- Week 1: Mathematical Basics 1 – Introduction to Machine Learning, Linear Algebra
- Week 2: Mathematical Basics 2 – Probability
- Week 3: Computational Basics – Numerical computation and optimization, Introduction to Machine Learning packages
- Week 4 : Linear and Logistic Regression – Bias/Variance Tradeoff, Regularization, Variants of Gradient Descent, MLE, MAP, Applications
- Week 5 : Neural Networks – Multilayer Perceptron, Backpropagation, Applications
- Week 6 : Convolutional Neural Networks 1 – CNN Operations, CNN architectures
- Week 7 : Convolutional Neural Networks 2 – Training, Transfer Learning, Applications
- Week 8 : Recurrent Neural Networks ¬– RNN, LSTM, GRU, Applications
- Week 9 : Classical Techniques 1 – Bayesian Regression, Binary Trees, Random Forests, SVM, Naïve Bayes, Applications
- Week 10 : Classical Techniques 2 – k-Means, kNN, GMM, Expectation Maximization, Applications
- Week 11 : Advanced Techniques 1 – Structured Probabilistic Models, Monte Carlo Methods
- Week 12 : Advanced Techniques 2 – Autoencoders, Generative Adversarial Networks
Recommended Books
Some books reccommended by NPTEL for this course:
-
Deep Learning, Goodfellow et al, MIT Press, 2017
The online version of the book available for free: deeplearningbook.org -
Pattern Recognition and Machine Learning, Christopher Bishop, Springer, 2009
The PDF version of the book available for free: PRML -
Deep Learning with Python, François Chollet, Manning Publications 2017
Not free. See the topics covered in the book in publisher’s page -
References to research papers will be provided through the course.
Matlab, Python or R?
The course syllabus and recommended books indicates python is the language you need to know for this course. The instructor may use Matlab for giving examples. If you have any programming experience, you can understand what is going on. If you happened to know R or Matlab, you can use that knowledge for solving assignment problems. But if you don’t know those languages, not at all need to worry. You can achieve anything using python!
If you didn’t set up python environment in your local machine or want to share the code with friends, try Colab.
Disclaimer (or about me!)
I have no relations with NPTEL to make any formal statement about this course. This page created for helping my coursemates! My qualification are eight years experience in software industry, Bsc-Statistics, Master of computer science, UGC NET (CS). So I have decent understanding of statistics, mathematics and computer science.