Видео

thank you so much sir

Valuable? Indeed! Very well-explained, comprehensive and concise. What I love the most is how you explain, which makes every concept easily comprehensible (the same as in your book).

Sir, i understood the explanation very well too my understanding .like the police and robber equation are we trying to find the best dose ? And what is the forgetfulness score for the dose is? Am just trying to understand what that 1.76 and -0.469 are in real world terms

thank you sir

looks if AI is there.

thanks a lot sir

Dear Dr. Jon Krohn, My name is MD. Golam Rabbany, and I am from Bangladesh. I aspire to become an AI engineer. Although I currently lack a personal computer, I am actively preparing by practicing mathematics on Khan Academy and improving my English communication skills through RUclips tutorials. I frequently reflect on my future study plans and eagerly anticipate the day I can begin studying Machine Learning (ML) with my own computer. However, through my research, I've realized that mathematics can be a significant challenge for many, including myself. I find your videos, and those of other related channels, incredibly helpful. Your in-depth knowledge of ML and the underlying mathematics is evident. Therefore, I humbly request that you consider creating a video series based on a book like "Mathematics for Machine Learning" by Marc Peter Deisenroth, or any other book you deem suitable. I would particularly appreciate if these videos were "pen and paper friendly," allowing viewers to follow along and learn effectively even without access to advanced software or computational resources. I am eager to embark on my mathematics learning journey with your guidance. Sincerely, MD. Golam Rabbany

Hello @JonKrohnLearns, are there exercises for coding? so that we could cement the knowledge in our brain also, aside from pen and paper exercises. Thanks for the response!

very good lectures. Thank you so much

2025 Thank you sir❤ Will be studying

New sub sir❤

Great tutorial learned a lot

What is the use of all this operation?

Wow 😳. Thankyou so much🎉

Amazing 🤩😍

Hi @JonKrohnLearns, thank you for this series! It seems very promising for beginners, however, I am having issues following along with the Python coding. Mainly, that the notebooks in your repository includes an older version of TensorFlow, which makes reproducing your code very challenging. Are there any plans to update these? Thanks!

computer science student need this!

Just wanted to point it out. Indians had been practicing mathematics long before other civilizations even existed. Please fact-check before providing information about history.

Hey Mr. John! I would like to ask you if you ever continue recording your videos. Please try to place your cursor somewhere at the center of the screen. The part at 9:23 is covered by subtitles, and in Udemy, the subtitles cannot be moved from the bottom.

Thanks you, bro, you have shown where we use matrix multiplication. I got satisfied and want to learn more in the field of AI and ML.

It's probably too late to ask but: The cops and robbers example makes sense to me, but in the house example, looking at say the bx1 term representing distance from school, what is unknown about it? Are we looking a single vale of x1 that applies to all the equations in the system the way we had a single distance and time in the cops and robbers example? And what would it even mean?

Thanks for this video

imagine teaching a class of 14 thousand people your a goat.

😮

heyyy, this feels like a wonderful series, this will be my stop fo MML. I hope by the time I reach this video, you start resuming the series!

youve helped so many people with this course especially me!

i hope your pillow is cold on both sides tonight.

Thank you for everything you do Dr. Krohn ❤😊

excellent! however the second order derivative of distance over time must be velocity not acceleration :)

Your explaination is crystal clear ! The way you explained the eigen vectors not only mathematically, but also through numpy and pytorch made me learn many things. Thanks :)

Thank you for sharing your knowledge. Brilliant.

Why didn't we make the y in yhat- true y 0 when we were taking out the derivative of yhat? Is it related to what you said earlier that regardless of y's irrelevance while the other variable is being differentiated, we still mention it? Or is it bcs of the comparison of yhat and true y

Really good!!!

Watched both linear algebra and calculas, it helped a lot.

Excellent. Thank you for sharing your knowledge.

Hi i think your answer to the linear algebra question is a bit ambiguous. Q1. It is 25minutes from the sheriff's perspective (t+5) but its 30 minutes from the system's perspective. It could be worded, how long does the robber keep away from the sheriff? since this fits t=0 from the robbers perspective and makes (t-5).

Have you taught till Optimization in your Udemy course? If not then for God's sake, pls do continue. I am just your videos away from being an ML engineer. Pls take out some time from your busy schedule and complete the course. Me begs 🙏

My goal is to do it with no supportive gear..then squat clean it! Lol 😅 that would be not awesome..no...it would be purely badass! 😂

damn, I'm 17, Brazilian and yet I did understand your content in a great way. thanks!!!

Thank you sir for the class! Till now without understanding the concept we studied But now you made it clear

import numpy as np # first matrix matrix_1 = np.array([[1,0,0], [0,1,0], [0,0,1]]) # take out the columns into individual matrix. v1 = matrix_1[:, 0] v2 = matrix_1[:, 1] v3 = matrix_1[:, 2] print(v1) print(v2) print(v3) # if dot product of any 2 vector is 0, then 2 vectors are orthogonal to each other. print(np.dot(v1, v2)) print(np.dot(v1, v3)) print(np.dot(v2, v3)) # if the norm is 1 then it is unit norm. print(np.linalg.norm(v1)) print(np.linalg.norm(v2)) print(np.linalg.norm(v3)) # now with second matrix matrix_2 = np.array([[2/3, -2/3, 1/3], [1/3, 2/3, 2/3], [2/3, 1/3, -2/3]]) # take out the columns into individual matrix. v1 = matrix_2[:, 0] v2 = matrix_2[:, 1] v3 = matrix_2[:, 2] print(v1) print(v2) print(v3) # if dot product of any 2 vector is 0, then 2 vectors are orthogonal to each other. print(np.dot(v1, v2)) print(np.dot(v1, v3)) print(np.dot(v2, v3)) # if the norm is 1 then it is unit norm. print(np.linalg.norm(v1)) print(np.linalg.norm(v2)) print(np.linalg.norm(v3))

i cant find the github repository

Loved these . Brilliant Course.

👌👌👌👌well explained

This blows my mind. 😮

I have found treasure. Thank you Mr. Jon

this is the best course in ML ever, thanks a lot!!

Very good!

Might be given by my level of English, but at the start of the video, there's a statement "a determinant is a special scalar value that we can calculate for any given matrix", but the first slide mentions square matrices as the only ones for which determinant is defined. Many sources (including Wikipedia) mention also just square matrices, but Google returns some guides how to compute determinants of non-square matrices. 😁

Very good. Thank You.