Mathematical Foundation For Machine Learning and AI (Udemy.com)

Learn the core mathematical concepts for machine learning and learn to implement them in R and python

( 257 Reviews )

Created by: Eduonix Learning Solutions

Produced in 2018

What you will learn

Refresh the mathematical concepts for AI and Machine Learning
Learn to implement algorithms in python
Understand the how the concepts extend for real world ML problems

Quality Score

Content Quality

Video Quality

Qualified Instructor

Course Pace

Course Depth & Coverage

Overall Score : 76 / 100

Course Description

ArtificialIntelligence has gained importance in the last decade with a lotdepending on the development and integration of AI in our dailylives. The progress that AI has already made is astounding with theself-driving cars, medical diagnosis and even betting humans atstrategy games like Go and Chess.
Thefuture for AI is extremely promising and it isn't far from when wehave our own robotic companions. This has pushed a lot of developersto start writing codes and start developing for AI and ML programs.However, learning to write algorithms for AI and ML isn't easy andrequires extensive programming and mathematical knowledge.
Mathematicsplays an important role as it builds the foundation for programmingfor these two streams. And in this course, we've covered exactlythat. We designed a complete course to help you master themathematical foundation required for writing programs and algorithmsfor AI and ML.
Thecourse has been designed in collaboration with industry experts tohelp you breakdown the difficult mathematical concepts known to maninto easier to understand concepts. The course covers three mainmathematical theories: Linear Algebra, Multivariate Calculus andProbability Theory.
LinearAlgebra Linear algebra notation is used in Machine Learningto describe the parameters and structure of different machinelearning algorithms. This makes linear algebra a necessity tounderstand how neural networks are put together and how they areoperating.
It covers topics suchas:

Scalars, Vectors, Matrices, Tensors
Matrix Norms
Special Matrices and Vectors
Eigenvalues and Eigenvectors

MultivariateCalculus This is used to supplement the learning part ofmachine learning. It is what is used to learn from examples, updatethe parameters of different models and improve the performance.
It covers topics suchas:

Derivatives
Integrals
Gradients
Differential Operators
Convex Optimization

ProbabilityTheory The theories are used to make assumptions about theunderlying data when we are designing these deep learning or AIalgorithms. It is important for us to understand the key probabilitydistributions, and we will cover it in depth in this course.
It covers topics suchas:

Elements of Probability
Random Variables
Distributions
Variance and Expectation
Special Random Variables

Thecourse also includes projects and quizzes after each section to helpsolidify your knowledge of the topic as well as learn exactly how touse the concepts in real life.
Atthe end of this course, you will not have not only the knowledge tobuild your own algorithms, but also the confidence to actually startputting your algorithms to use in your next projects.
Enrollnow and become the next AI master with this fundamentals course!Who this course is for:

Any one who wants to refresh or learn the mathematical tools required for AI and machine learning will find this course very useful

Time: 4.5h

Instructor Details

Eduonix Learning Solutions

3.8 Rating
257 Reviews

Eduonix creates and distributes high quality technology training content. Our team of industry professionals have been training manpower for more than a decade. We aim to teach technology the way it is used in industry and professional world. We have professional team of trainers for technologies ranging from Mobility, Web to Enterprise and Database and Server Administration.

Machine Learning with Python by Sentdex (2016)

4.6 (15 Reviews)

Provider: YouTube
Time: 19h

Free

Practical Deep Learning for Coders, v3 (2019)

4.3 (20 Reviews)

Provider: fast.ai
Time: 30h

Free

Applied Machine Learning in Python (2016)

4.9 (481 Reviews)

Provider: Coursera
Time: 7h

Free

More Courses

Reviews

3.8

257 total reviews

5 star 4 star 3 star 2 star 1 star

Write a Review

By Lakhan Soren on 12/20/2020

Great overview. Loved it.

By Jacob Vandersteen on 12/13/2020

Yay

By Fleming Hilskov on 11/7/2020

It is difficult to follow when he speaks about things on the screen without pointing at them, use a digital pen. He speak very fast.

By Sanish Nair on 11/3/2020

Not at all helpful

By Ramakrishna k on 10/13/2020

nice demonstration ...

By Francesco Simonetti on 10/11/2020

Good fundamentals, recommended.

By Development Silicon Syrup on 10/5/2020

I like the way he is presenting and explaining the topics. He did rush through the probability theory, which is the most important part. I would like the instructor to provide more concrete examples of Laplace and Exponential Distribution.

By Nihar Dutta on 9/26/2020

This course is much like a table of content of a very large book. You will know the terminology and brief descriptions. Then, it's up to you to dive into the each topic. Sometimes, it's too brief to understand anything about the topic. For example: The last chapter on the special random variables.

By Hannes Foulds on 9/16/2020

This is a truly terrible course, do not buy it, look elsewhere if you want something of value. All this seems to be is a kid rambling off some definitions and showing equations all at a very high level with no practical demonstration of how it relates to ML or AI. Unless you already understand the topics presented very little would make sense, and then why are you looking at this course?

By S.Thalapathiraj on 9/7/2020

EXCELLENT

By Alpha Ly on 9/6/2020

It seems to me that the person who's talking in the video is not actually the one who produced the lesson. You can't know and be that far in math and statistics concepts and say " Matrices multiplication is not communitive" instead of "commutative".
He sometimes say "Matricee" instead of "Matrice". And many more. That is discouraging.

By Rajesh Banka on 8/16/2020