Course Information
Registration period
Year-round Recruitment
Course Level
Study Mode
Duration
16 Hour(s) 25 Minute(s)
Language
English
Taught by
Dr Jon Krohn, SuperDataScience Team, Ligency
Rating
4 views
Course Overview
Essential Linear Algebra and Calculus Hands-On in NumPy, TensorFlow, and PyTorch
Mathematics forms the core of data science and machine learning. Thus, to be the best data scientist you can be, you must have a working understanding of the most relevant math.
Getting started in data science is easy thanks to high-level libraries like Scikit-learn and Keras. But understanding the math behind the algorithms in these libraries opens an infinite number of possibilities up to you. From identifying modeling issues to inventing new and more powerful solutions, understanding the math behind it all can dramatically increase the impact you can make over the course of your career.
Led by deep learning guru Dr. Jon Krohn, this course provides a firm grasp of the mathematics — namely linear algebra and calculus — that underlies machine learning algorithms and data science models.
Course Sections
Linear Algebra Data Structures
Tensor Operations
Matrix Properties
Eigenvectors and Eigenvalues
Matrix Operations for Machine Learning
Limits
Derivatives and Differentiation
Automatic Differentiation
Partial-Derivative Calculus
Integral Calculus
Throughout each of the sections, you'll find plenty of hands-on assignments, Python code demos, and practical exercises to get your math game in top form!
This Mathematical Foundations of Machine Learning course is complete, but in the future, we intend on adding extra content from related subjects beyond math, namely: probability, statistics, data structures, algorithms, and optimization. Enrollment now includes free, unlimited access to all of this future course content — over 25 hours in total.
Are you ready to become an outstanding data scientist? See you in the classroom.
Course Content
- 10 section(s)
- 114 lecture(s)
- Section 1 Data Structures for Linear Algebra
- Section 2 Tensor Operations
- Section 3 Matrix Properties
- Section 4 Eigenvectors and Eigenvalues
- Section 5 Matrix Operations for Machine Learning
- Section 6 Limits
- Section 7 Derivatives and Differentiation
- Section 8 Automatic Differentiation
- Section 9 Partial Derivative Calculus
- Section 10 Integral Calculus
What You’ll Learn
- Understand the fundamentals of linear algebra and calculus, critical mathematical subjects underlying all of machine learning and data science
- Manipulate tensors using all three of the most important Python tensor libraries: NumPy, TensorFlow, and PyTorch
- How to apply all of the essential vector and matrix operations for machine learning and data science
- Reduce the dimensionality of complex data to the most informative elements with eigenvectors, SVD, and PCA
- Solve for unknowns with both simple techniques (e.g., elimination) and advanced techniques (e.g., pseudoinversion)
- Appreciate how calculus works, from first principles, via interactive code demos in Python
- Intimately understand advanced differentiation rules like the chain rule
- Compute the partial derivatives of machine-learning cost functions by hand as well as with TensorFlow and PyTorch
- Grasp exactly what gradients are and appreciate why they are essential for enabling ML via gradient descent
- Use integral calculus to determine the area under any given curve
- Be able to more intimately grasp the details of cutting-edge machine learning papers
- Develop an understanding of what’s going on beneath the hood of machine learning algorithms, including those used for deep learning
Skills covered in this course
Reviews
-
PPraveen Reddy
The course doesn't have the entire content. Instructor have said that new videos would be added but still they are not there yet
-
MMiha Mok
The course is great and the instructor is also great and enthusiastic. Although I already knew a lot of the stuff presented here, I think I gained a deeper understanding. I also think the jupyter notebooks provided are a very good resource and also very nice to review on your own from time to time. However, there are 2 minor and 1 major problems: - minor: a lot of the math is high school level (especially on derivatives) - minor: not a whole lot of actual comprehension checks / assignments. I know it's on each individual to take what they can from the course, but still, I feel like there could be more Even with these two, it would probably be a 4.5 star course if if wasn't for the big problem; the missing sections. A lot of people pointed this out, and as far as I can tell, the sections are on O'Reilly. What bothers me is how much he talks about how the last section will tie it all together, but then it's not there. It exists, just not on Udemy. Jon, if you are somehow reading this - if you add the missing sections, I will update my review to 4.5 stars.
-
JJavi S.
Kind of mixed feelings about this course with a bit of bitter disappointment... NOT Good: -> Mathematical content is extremely shallow. Just some refreshers on derivatives , integrals and linear algebra that are taught in last year of school / first year of university. More advanced cool concepts such as SVD Decomposition are not taught in paper, just going through the corresponding Python method. Course title is kind of misleading in this way IMO. Obviously the derivative is the foundation of many ML algorithms, but I did not expect to review concepts such as the derivative of a constant. I thought that was assumed to be known in math ML course. -> The course is incompleted. The instructor repeats the course syllabus at the beginning of each segment and there are 3 and a half lessons missing. Also is kind of frustrating because it seems that all the highschool math refreshers build up to the last two lesson on Statistics and Optimization, but those are not available in the course content :( Good: -> I actually learnt a reasonable deal of Python programming. I was kind of a newbee and I feel more confident with numpy and matplot. Also Pytorch to some extent. In the end, is a great pratice for a Python beginner. -> Notebooks are a great resource, specially to look up some matplot code to enhance your plots if you dont have a lot of experience that way. -> The instructor is great. Even if the content was extremely easy, I ended up pushing through the whole course, and trying to make the best of it, beacuse of him. You gotta love the guy. He keeps you engaged and his enthousiasm is contagious. It feels like he really enjoys teaching and he really knows ML, even if the course is really basic level math.
-
JJ. Diego Ramirez
I have a mathematics background and had used PyTorch before, so I knew the theory and I was here mainly to have a grasp of TensorFlow. Jon did a great job but I am hoping he can upload more videos on the rest of the notebook of Probability Theory, as we only scratched the surface.
