Online Course Highlights

Prof. Ganapathy & Prof. Balaji Srinivasan via NPTEL
Co-ordinated by: IIT Madras
12 Weeks Duration
Discipline: Computer Science and Engineering
Language: English

This is a Machine Learning for Engineering and Science Applications course coordinated by IIT Madras. It is a detailed course for individuals who are looking forward to learning every little detail about Machine Learning for Engineering and Science Applications. This is a 12 weeks long course. The entire course is divided into different modules, and every week contains different topics. Boost your resume with our Accredited Machine Learning Programs that are recognized globally.

What will you learn through this Course?

Let us look at what topics will be covered each week:

Week 1

The first week of this course comprises of introduces to Artificial intelligence, along with its history. In addition to this, the instructor will also guide you through the overview of Machine learning along with the fundamentals of Linear Algebra. Once you are done with linear algebra, you will move forward to learning about the Basic operation and norms.

Week 2

Moving onto week 2, you will start this week by learning about the probability theory of discrete and continuous random variables. Moving on, you will cover topics such as expectation, Variance Covariance, and Bayes’ Theorem.

Week 3

Following up to week 3, you will get familiar with the advanced matric calculations. Aiding to learning about constrained optimization, unconstrained optimization, and introduction to packages.

Week 4

You will learn about Coding linear regression, and you will get to understand an example of linear regression. This week, you will be covering topics such as the Goodness of fit, etc.

Week 5

Throughout week 5, you will be covering a lot. You will start by getting introduced to Deep learning, followed by logistic regression, and the Binary Entropy cost function. Once you are done with the first few topics, you will start to differentiate the sigmoid, etc.

Week 6

This week has planned for you to get familiar with the Convolution Neural Networks CNN. Once you get familiar with CNN, you will start earning its types.

Week 7

In this week you will cover topics such as Train Network for Image Classification, Semantic Segmentation, and Hyperparameter optimization. Moreover, you will also develop an understanding of Transfer Learning, etc.

Week 8

Moving on to week 8, you will start by learning about Activation functions and learning rate decay. Once you are familiar with those topics, you will learn about Data Normalization, Batch Norm, etc.

Week 9

This week will help you to get familiar with the topics of KNN, Binary decision trees, Binary regression trees, Bagging, Random Forest, etc.

Week 10

This week supports the knowledge of Probability Distributions- Gaussian, Bernoulli, and Covariance Matrix of Gaussian Distribution. Additionally, you will also learn about NaÃ¯ve Bayes, MLE Intro, and PCA parts 1 and 2.

Week 11

In the second last week of the course, you will develop knowledge for MLE, MAP and Bayesian Regression, and Generative Adversarial Networks (GAN). Not only this but also Variational Auto-encoders (VAE), etc.

Week 12

The last week of the course is all about application. You will be understanding the application of Fin Heat Transfer, Computational Fluid Dynamics. Topology Optimization, and PDE/ODE using Neural Networks.

More Related Courses:

Structuring Machine Learning Projects

- - DeepLearning.ai via Coursera
  - 5 hours of effort required
  - 308,994+ already enrolled!
  - ★★★★★ (44,735 Ratings)

Machine Learning

- - Stanford University via Coursera
  - 64 hours of effort required
  - 3,768,682+ students enrolled
  - ★★★★★ (151,613 Ratings)

Your Feedback:

Excellent Course

March 11, 2021

Mesmerizing videos. Excellent and simple explanation. Highly recommend students to attend this course.

Jayanthi Raghavan

5.0

5.0 out of 5 stars (based on 1 review)

Excellent100%

Very good0%

Average0%

Poor0%

Terrible0%

Course Review: Machine Learning for Engineering and Science Applications