I really don't like how courses and videos just say it's ok if you don't know calculus, statistic, linear algebra... Dude, it's not a monster, everyone can learn it. So go back, study the pre-requesites, and then you will actually understand how machine learning algorithms work.
This is the best quick explanation of machine learning I have seen to date. You covered the first few weeks of the course extremely well and concisely. I shared with all my friends to get them more hyped about machine learning!
This has been one of your best videos. Is the math you are using with the examples of the price of a house and passing or failing a test statistics, calculus, mathematical modelling, or probability?
Can all the questions you used the computer to help you answer be answered by doing the math with a pencil, a paper, and with or without a calculator? Do you have to know graph theory to be able to solve and or answer problems like the examples you showed in this video?
This is probably the most explanatory video I've ever seen for a beginner. Please continue making more videos about the mathematics of machine learning and how they're applied
With gradient descent, we generally don't update one parameter and 'then' another. Rather, parameter updates are done simultaneously. Great video overall. I like how you started with a simple model structure and skipped the derivations to keep things understandable to a broader audience.
I already took the Coursera course, but BOI was this a good refresher. Also helps me as a CS major have a clearer idea of what math I'll need to take. Thanks again!
UPDATE: Machine Learning and my other big CS interest, parallel programming, have pushed me to learning Linear Algebra SO much that I made that the first advanced math class I'll take after getting past Calc 2. (I can choose between Calc 3/Multivariable Calc vs. Linear Algebra vs. Differential Equations)
@@projectjt3149 I thought it's recommended you learn both Linear Algebra and Multivariable? I've already taken the former along with probability, and I have to take calc 3 this summer before ML in the fall
@mathsonboard It does. It introduces a little bit of algebra and the course walks you through a lot of projects on different kinds of machine learning, ie computer vision. Unfortunately, the course is taught in Octave, but someone did make a series of Medium articles where they wrote the Python version of the code.
This is a great explanation of a very complex subject. While incorporating and utilizing such a topic doesn't require an intense understanding of the process, it does help to share the facts with others.
Toward the end of the video, I think an important note to make is that multilayer neural networks need some sort of activation function (i.e. ReLU) to be considered nonlinear. The sum of a bunch of linear weight multiplications is still linear so the activation is required to make it nonlinear. I think this is especially important to note because the neural networks were explicitly introduced as a way to make machine learning nonlinear. Good video!
Thankyou so much for making this video giving a gist of the mathematics behind machine learning, and getting me excited about undergoing courses in this field.
Nice video! Hands down your channel has delivered the most useful information to me and my future. Not to mention interesting videos like this one. I've been doing discrete math stuff and so it's refreshing to learn about more continuous and applied math concepts.
Hey it would be great if u could do a machine learning course for complete beginners, here on UA-cam. I really enjoyed this vedio! Thanks you so much for this!!
The class he mentioned, Andrew Ng's Intro to Machine Learning, is an incredibly well taught machine learning course with videos, quizzes, programming assignments, and a certificate. I highly recommend you take it.
Major prep, every time I am losing hope you publish a great video such as this one to keep me going. No wonder you are so bright you can explain the topics you learned at University and explain it to us High school students to understand, Thank you MP its a blessing to come across your channel.
Thanks for the comment! And I probably wouldn't put priority on going to an ivy league. Maybe I'd apply but I think UCLA would be a top choice for me because it's a good school and I live close so would be a little more convenient.
Thank you for making this types of vdo I am very much interested for maths and now I'm learning the application of different maths from your channel. I'm a computer science student. Again thank you very much.
6 років тому+1
Sigmoid functions are a group of functions that have an S-like curve and arcus tangent and even signum function are sigmoid functions. The f function in the video is just one of the possible sigmoid functions called logistic function.
Hard reality - the harder and complex the project is the more math (a better and efficient solutions) is needed,so you do need math ...the more you know about math and actually imp part is how to apply them in your problem.. So good part is that we can learn mathematics through practice.. I myself is not good at math ,but i will learn it by giving a great deal time and concentration.. I am ready for it ..I won't scared because of math.. 😤😤
I'm learning ML. I've never seen such a beautiful introduction.. I know the concepts are much attractive & a bit difficult as well.. How did you do it man?? I'm spellbound..haha.. really I'm overwhelmed
I'm in the 7th grade I'm really really eager to learn this im going to keep watching until I get it I math is amazing and learning this is fascinating to me I cant wait to be an ai engineer just need to understand this earlier so I'm ahead
I am an idiot. But power to you! Just use your powers for good, when you get there. Math can be fun, with a bit of brain conditioning. I just learned that too late in life. Good luck.
Andrew Ng is the best!!! I thoroughly enjoyed taking that machine learning class from him last summer. I learned the most I had ever learned in a class.
Thank you for your video. I was wondering if you've done an electrical engineering degree would you have enough of the relevant math covered to go into machine learning/ artificial intelligence or would you need to take some extra classes? I'm guessing statistics would be needed, but what about everything else? Thank you again. Keep up the good work
At my university the prerequisites of machine learning course are linear Algebra, calculus 2 and probability which are all covered in EE program :) But if you are still a student in sophomore year I suggest you to switch to computer engineering since studying EE will leave you have little to no time for other interests such as ML unless you are great at managing your time.
Based on what I've seen, yes the math I learned in EE was plenty to get started with machine learning since I took up to multivariable calculus, linear algebra, and a statistics class for engineers. Later on there's probably more theory especially in statistics but the math that most engineers see is plenty to get you started.
@ S M As long as you know linear algebra, multivariable calculus, and statistics that is a good solid foundation to start. Knowing some probability theory would be beneficial as well.
It also depends on the field you are actually interested in. For example, when I was taking digital signal processing courses I had an intense introduction to stochastic gradient decent optimisation, neural networks, and a lot of statistics. So if you want to be prepared to proceed with ML in the future, DSP courses will be very useful.
I believe the equation m(new) = m(current) - k(dE(m)/dm) is kown as "Newton's methode" for finding the zero of function f(x), in this case f(x) is just the derivative of the parabola he plotted.
Great video. I studied Applied Maths, and it's interesting to see how most of the theory becomes more fascinating when applied in Machine Learning. There's also Pure Maths which covers areas such as Graph Theory, Logic, Topology.Maths is truly beautiful.
After watching this video if any beginners wants to learn more about math in machine learning I would like to recommend Andrew Ng's Coursera course also available in UA-cam.
In gradient descent, How are you choosing a new value to ‘guess’ as the gradient of the price vs sq footage graph line using the error curve when the error curve doesn’t yet exist, and requires you to choose another point to guess?
Check out the Machine Learning Course on Coursera: click.linksynergy.com/deeplink?id=vFuLtrCrRW4&mid=40328&murl=https%3A%2F%2Fwww.coursera.org%2Flearn%2Fmachine-learning%3FDmp_ml_nov18
Awesome video. You keep getting better and showcasing more interesting subjects I love it! Quick question though, where did you get the space artwork behind you? I really like the size and simplicity of it!
Good explanation, I found the percentage example hard to understand though, probably just me. It is counter-intuitive as we would assume a binary result should have straightforward way to reduce the error but is more complex.
I am 11 and I have a youtube channel where I explain differnt programming concepts. This video was very clear and well explained and you helped me understand many complex algorithems such as gradient decent. I subscribed and liked the video! 😃
It's the same thing. Perhaps "Data Mining" is more focused on certain methods sometimes, but really to "mine" data is the same as to learn automatically.
"If you don't know calculus, that's OK"
*continues to talk about calculus*
*Picks up Deep Learning by Goodfellow, Bengio and Courville. Doesn't understand a word. Orders Calculus for Dummies.*
andrew ng
MachinLearning 2020! IN MY CHANNEL
I really don't like how courses and videos just say it's ok if you don't know calculus, statistic, linear algebra... Dude, it's not a monster, everyone can learn it. So go back, study the pre-requesites, and then you will actually understand how machine learning algorithms work.
🤣🤣🤣
This is the best quick explanation of machine learning I have seen to date. You covered the first few weeks of the course extremely well and concisely. I shared with all my friends to get them more hyped about machine learning!
Thanks man! Really appreciate the comment and sharing the video, helps a lot.
@ Cameron McWilliams ua-cam.com/video/Cr6VqTRO1v0/v-deo.html
MachinLearning 2020! IN MY CHANNEL
This has been one of your best videos. Is the math you are using with the examples of the price of a house and passing or failing a test statistics, calculus, mathematical modelling, or probability?
Can all the questions you used the computer to help you answer be answered by doing the math with a pencil, a paper, and with or without a calculator? Do you have to know graph theory to be able to solve and or answer problems like the examples you showed in this video?
The subtle "used to demonetize your favorite videos across this entire platform." Savage
Susan Wojcicki is showing her true colors as an unintellectual SJW by her choice of what she demonetizes.
Now TikTok is better than youtube
for real, zach don't fuck around lol
MachinLearning 2020! IN MY CHANNEL
@@landosllim4576 Zach ain't bitch made.
This topic is explained in depth in Linear algebra.
Halo 1player?? You got discord?
Any good PDFs out there?
Jonathan Molina Linear Algebra and Its Applications...search for this book there is a free pdf ...
I couldnt find the download :/ is there a link ?
This is probably the most explanatory video I've ever seen for a beginner.
Please continue making more videos about the mathematics of machine learning and how they're applied
With gradient descent, we generally don't update one parameter and 'then' another. Rather, parameter updates are done simultaneously. Great video overall. I like how you started with a simple model structure and skipped the derivations to keep things understandable to a broader audience.
Agree
I already took the Coursera course, but BOI was this a good refresher. Also helps me as a CS major have a clearer idea of what math I'll need to take. Thanks again!
UPDATE: Machine Learning and my other big CS interest, parallel programming, have pushed me to learning Linear Algebra SO much that I made that the first advanced math class I'll take after getting past Calc 2. (I can choose between Calc 3/Multivariable Calc vs. Linear Algebra vs. Differential Equations)
@@projectjt3149 I thought it's recommended you learn both Linear Algebra and Multivariable? I've already taken the former along with probability, and I have to take calc 3 this summer before ML in the fall
@mathsonboard It does. It introduces a little bit of algebra and the course walks you through a lot of projects on different kinds of machine learning, ie computer vision. Unfortunately, the course is taught in Octave, but someone did make a series of Medium articles where they wrote the Python version of the code.
This is a great explanation of a very complex subject. While incorporating and utilizing such a topic doesn't require an intense understanding of the process, it does help to share the facts with others.
Toward the end of the video, I think an important note to make is that multilayer neural networks need some sort of activation function (i.e. ReLU) to be considered nonlinear. The sum of a bunch of linear weight multiplications is still linear so the activation is required to make it nonlinear. I think this is especially important to note because the neural networks were explicitly introduced as a way to make machine learning nonlinear.
Good video!
Thankyou so much for making this video giving a gist of the mathematics behind machine learning, and getting me excited about undergoing courses in this field.
Nice video! Hands down your channel has delivered the most useful information to me and my future. Not to mention interesting videos like this one. I've been doing discrete math stuff and so it's refreshing to learn about more continuous and applied math concepts.
Dude how did you read my mind?i really needed this video..Thanks a lot
lol I was thinking the same thing, he literally gave the exact explanation I so needed to finally understand this shit.
Machine learning ur needs soon they will tell you what to do
Go to Coursera do do the course for free
Go to the stanford's one, that were he took the examples and the graphs from.
UA-cam algorithm machine learning
Im glad i discovered both your tech and your comedy channel. The only regret I have is not discovering these earlier. Thank you for the content.
Hey it would be great if u could do a machine learning course for complete beginners, here on UA-cam. I really enjoyed this vedio! Thanks you so much for this!!
The class he mentioned, Andrew Ng's Intro to Machine Learning, is an incredibly well taught machine learning course with videos, quizzes, programming assignments, and a certificate. I highly recommend you take it.
@@camozot thank you so much for the info!!
This video is sponsored by Coursera dummy guess where you will find the course for this
I'm thinking too
MachinLearning 2020! IN MY CHANNEL
Excellent video. More precise and enlightening than many MOOCs out there.
0:46 OMG that burn!!!
Major prep, every time I am losing hope you publish a great video such as this one to keep me going. No wonder you are so bright you can explain the topics you learned at University and explain it to us High school students to understand, Thank you MP its a blessing to come across your channel.
Btw weird question... Since you have a 3.8 gpa are you looking to study in ivy league schools, for your masters degree?
Thanks for the comment! And I probably wouldn't put priority on going to an ivy league. Maybe I'd apply but I think UCLA would be a top choice for me because it's a good school and I live close so would be a little more convenient.
If you're losing hope as a hs student just wait until college lol.
You did a phenomenal job explaining this. Thanks a lot!
I took the course and you went through it pretty well
Thank you for making this types of vdo
I am very much interested for maths and now I'm learning the application of different maths from your channel.
I'm a computer science student.
Again thank you very much.
Sigmoid functions are a group of functions that have an S-like curve and arcus tangent and even signum function are sigmoid functions. The f function in the video is just one of the possible sigmoid functions called logistic function.
Hard reality - the harder and complex the project is the more math (a better and efficient solutions) is needed,so you do need math ...the more you know about math and actually imp part is how to apply them in your problem..
So good part is that we can learn mathematics through practice..
I myself is not good at math ,but i will learn it by giving a great deal time and concentration..
I am ready for it ..I won't scared because of math..
😤😤
I'm learning ML. I've never seen such a beautiful introduction.. I know the concepts are much attractive & a bit difficult as well.. How did you do it man?? I'm spellbound..haha.. really I'm overwhelmed
I have master of science in hydraulics and you explained most of this stuff way better that my profs back then. 10/10
This is probably the best video on the subject I have ever watched. Thumb up
Superb explanation sir! I'm glad atleast some people are doing the job of spreading knowledge free of cost.... 😊
I'm in the 7th grade I'm really really eager to learn this im going to keep watching until I get it I math is amazing and learning this is fascinating to me I cant wait to be an ai engineer just need to understand this earlier so I'm ahead
You have seen nothing not even a single.drop of maths my boy..
Awesome to hear! Keep that passion and drive, it will take you far. You'll see people like Sheela who will try to hold you back. Don't let em.
Start with linear algebra and then matrix manipulation
I am an idiot.
But power to you!
Just use your powers for good, when you get there.
Math can be fun, with a bit of brain conditioning. I just learned that too late in life.
Good luck.
Good Passion my boy
Ok this video was epic. Man i am thankful that i found your channel. This video just stimulated my mind. I might start learning it today.
Amazing content....Very beautifully and efficiently provided the intuition behind the algos
best machine learning explanatory video
An engineer and a programmer... amazing skills.
Can you do a "experimental vs theoretical physics. Which major to pick".
theoretical :) Happy to help.
Computational physics sounds like your kind of thing.
Unless you plan to do a PhD in somewhere like Switzerland or The Us don't Even think of experimental
Check out domain of science
You have a talent for explaining.
excellent work man! These videos help so much! thanks again.
Andrew Ng is the best!!! I thoroughly enjoyed taking that machine learning class from him last summer. I learned the most I had ever learned in a class.
15:34 The Matrix "Silent weapons for quiet wars".
Thank you for your video. I was wondering if you've done an electrical engineering degree would you have enough of the relevant math covered to go into machine learning/ artificial intelligence or would you need to take some extra classes?
I'm guessing statistics would be needed, but what about everything else?
Thank you again. Keep up the good work
At my university the prerequisites of machine learning course are linear Algebra, calculus 2 and probability which are all covered in EE program :)
But if you are still a student in sophomore year I suggest you to switch to computer engineering since studying EE will leave you have little to no time for other interests such as ML unless you are great at managing your time.
Based on what I've seen, yes the math I learned in EE was plenty to get started with machine learning since I took up to multivariable calculus, linear algebra, and a statistics class for engineers. Later on there's probably more theory especially in statistics but the math that most engineers see is plenty to get you started.
@@zachstar Thank you very much for your reply. That's really good news. I love how engineering has so many transferable skills.
@ S M
As long as you know linear algebra, multivariable calculus, and statistics that is a good solid foundation to start.
Knowing some probability theory would be beneficial as well.
It also depends on the field you are actually interested in. For example, when I was taking digital signal processing courses I had an intense introduction to stochastic gradient decent optimisation, neural networks, and a lot of statistics. So if you want to be prepared to proceed with ML in the future, DSP courses will be very useful.
I believe the equation m(new) = m(current) - k(dE(m)/dm) is kown as "Newton's methode" for finding the zero of function f(x), in this case f(x) is just the derivative of the parabola he plotted.
Yup, that's calc1 right there
very good video. nice overview, beautiful illustrations for a complex topic
This was so satisfying to watch
This is that god type video I got in the internet today. You’re awesome✌️
Can you make a video about PE license? I'm a forth year computer engineering student and I don't know if it's worth it to take the FE exam
I second this
Wow visualisation helped me a lot to understand sigmoid function better
So informative. Covers lot of basic starts
The dramatic music from 00:54 to 01:01 is hilarious XD
This was highly informative given that it is 16 min. thank you :)
Brilliant intuition build up....Bravo
as an industrial engineer I can say hat linear algebra is one of the most powerful tools of numerical methods, by a landslide
Best Explanation about gradient descent
Great video. I studied Applied Maths, and it's interesting to see how most of the theory becomes more fascinating when applied in Machine Learning. There's also Pure Maths which covers areas such as Graph Theory, Logic, Topology.Maths is truly beautiful.
Bro awesome video . keep up your good work...
Thank you very much. I have started studying for ML this was very helpful. Plz do make more videos on Machine learning, Deep Learning.
After watching this video if any beginners wants to learn more about math in machine learning I would like to recommend Andrew Ng's Coursera course also available in UA-cam.
You are a magical person
Thanks so much for your hard work
So i appreciate your hard working and share the information
Beautifully explained
Now I'm a big fan of Zach 🌟. 💜💜💜💞💞💞
dude, I love you your intelligence
Hello major prep you are bestttttttttt
part 2 please ☺.
loved your work.!
Thanks a lot, it's a great video. I hope you do another one about the way to become a data scientist.
In gradient descent, How are you choosing a new value to ‘guess’ as the gradient of the price vs sq footage graph line using the error curve when the error curve doesn’t yet exist, and requires you to choose another point to guess?
Can you do about Nuclear engineering next?
Pls
Very Good Teacher !
Check out the Machine Learning Course on Coursera: click.linksynergy.com/deeplink?id=vFuLtrCrRW4&mid=40328&murl=https%3A%2F%2Fwww.coursera.org%2Flearn%2Fmachine-learning%3FDmp_ml_nov18
Hey major prep which video editing app do you use??
Premier pro
@@zachstar hey could you please tell which application do you use to create these videos
Just what I've been looking for. Thank you so much
Did nobody else find the "linear/nonlinear" joke hilarious?
You're amazing bro
Nice video ... a lot of work
Good explanation. Thank you!
With simple math and complex algs you can achieve alot
Why do you square the error at 2:25? I didn't understand the explanation
So that errors like , say, 2.25 and -2.25 dont cancel each other to 0. Instead we get total error as 2.25^2 + (-2.25)^2
I watched this video last year before I was in Engineering school and I thought I'd never learn... Lol... Fast forward and these problems are doable.
Congrats mate. Keep it up and never stop learning ^^
@@TheScriptan Thanks sir
Why is this so good 😭
Excellent video
great video!
Please do a second video, very interesting!
Awesome video. You keep getting better and showcasing more interesting subjects I love it! Quick question though, where did you get the space artwork behind you? I really like the size and simplicity of it!
Thank you for the comment! I got all the artwork from amazon. There's actually 4 pics behind me and they were all sold together.
Make videos for ML beginners please. This video is excellent.
where did came from the algorithm that calculates the next slope m ? Does it have something to do about euler method ? Or another one ? minute 3:35
Thanks . I am.a java developer and electrical engineering grad . Wanted to learn machine learning
Nice!! I used course!!
Might be stupid question but why do we square instead of having absolute value in std ?
Good explanation, I found the percentage example hard to understand though, probably just me. It is counter-intuitive as we would assume a binary result should have straightforward way to reduce the error but is more complex.
Go back come back after 6 months after learning calculus, linear algebra and statistics
really benefit great help boost the understanding
Really Grateful the tutorial keep in touch
glad you enjoyed!
around 3:50, ain't that like chaos theory's predictivness sampling? or am i more lost than i think?
I did not expect that you would need to use the error function
I don't think he meant erf
MachinLearning 2020!
Uses page 2 of the lookup table
truth and fact is a fine line between dream and reality
Make a video regarding Data Science please. Thank you!
thanks broo greetings from colombia pereira capital del eje.
looks ez will try to learn it
Hey, MajorPrep! I really your videos! Can you please make a video about COMPUTATIONAL SCIENCE :)
I am 11 and I have a youtube channel where I explain differnt programming concepts. This video was very clear and well explained and you helped me understand many complex algorithems such as gradient decent. I subscribed and liked the video! 😃
Is Calculas need for learning AI or ML
Yes
@@codeintherough thank you
I got confused about why he plugged the obtained (1.2139) value into sigmoid function to find passing percentage.
So between Data Mining and Machine Learning which one is more important? Because some universities offer only DM while the others only have ML
It's the same thing. Perhaps "Data Mining" is more focused on certain methods sometimes, but really to "mine" data is the same as to learn automatically.
Nice im learning all 3 at my study, always a career change possible haha
Make a video for Data science / analytics!