have ML exam on Thursday and I am watching this.. after reviewing Andrew's coursera course, standford class, and MIT AI class.. This one is pretty clear.. Thank you. rush to your next video.
Thank you so much for doing this. As a person who doesn't have a strong math background, I really appreciate the work and effort you have put into this VDO. Thank you!!
I agree with Stas! This was a great video that simplified and clearly described SVM in a way that anyone can understand! Thanks for making these videos!
I really appreciate the work you have done. When you want to explore something new, it's extremely important to form an intuition for what you're dealing with. Otherwise, you will suffer from complex mathematics, even if you are good at it. Thanks to you, this is no longer a problem.
it's a great idea that you walk into the video. this way we can take a screen shot of the notes. also, if you do write anything on the board, throughout the video, then may be you can walk out of the camera view at the end. that might be really helpful. thanks
In your second figure, is the margin not defined as the distance between the decision boundary and the support vectors? So the distance you're illustrating is 2x margin? Other than that your videos are amazing. Thanks
@@ritvikmath , Thank you for the video. Generally outliers are removed before applying the algorithm, then still why outliers are used while considering the disadvantage of algorithm?
Can we use SVM? If we want to analyze repeated event (example sheetbreak, etc which happen once 1 month ) by reading historical data and give labels, 1 hour before break, 2 hours before break 3 hours before break up to 8 hours before break? . then we can do something to prevent that event, before it really hapenned What the best algorithm for this case if SVM is not suitable? Thankyou
What I find confusing is how only the support vectors are needed to determine the decision boundary. Surely you want your decision boundary to be dependent on all data points.
Because you’re trying to maximize the boundary, points not defining the boundary don’t need to be considered. Think of it like. If you were to remove that data point, would the boundary change?
clean, crispy and concise. bravo sir, and thank you
Man, I swear, I am so surprised you have so little views and likes - this is magnificent work. Thank you so much. Moving forward to the next videos.
I think it's because of his explanation is fascinating only to him to sound smart. It doesn't reach general audience
@@fatriantobong8169 Bro do you think before you speak?
Thanks for making my classes make sense! Professor explained this but not nearly as elegantly as you did!!
have ML exam on Thursday and I am watching this.. after reviewing Andrew's coursera course, standford class, and MIT AI class.. This one is pretty clear.. Thank you. rush to your next video.
Naturally talented for explaining complicated concept in simpler way.
Thank you so much for doing this. As a person who doesn't have a strong math background, I really appreciate the work and effort you have put into this VDO. Thank you!!
You have explained it like no one else. Keep up the good work.
I'm taking a course on udemy and watching all your videos afterwards. You explain things so well and make it so easy to understand!
Very intuitive explanation. Looking forward to the next video. Hoping for deeper understanding of this algorithm.
You've explained my professor's whole 13 part lesson in one 8min video!! thank you
Excellent delivery! Explained so clearly! The decision boundary is a line, plane or hyperplane. Well done!
I agree with Stas! This was a great video that simplified and clearly described SVM in a way that anyone can understand! Thanks for making these videos!
You make everything so easy and simple. You definitely deserve more subscribers.
Thank you so much! I always turn to your videos for the best, most intuitive explanations!
This man is the most slept on fr I appreciate your ds videos!
A talent teacher! Millions of thanks!
Thank you so much for making these videos! I'm looking forward to part two!
I really appreciate the work you have done. When you want to explore something new, it's extremely important to form an intuition for what you're dealing with. Otherwise, you will suffer from complex mathematics, even if you are good at it. Thanks to you, this is no longer a problem.
Your explanations are so easy to understand for math-untrained people like me. Thanks, and keep going
Great explanation, both concise and precise. Very good description of substantial properties of SVM.
This video deserves more views than it currently has .
thanks!
these videos are too underrated. thank you so much for your breaf and clear explanations. soooooo useful
thank you so much!!! 8 minutes is better than my 2 hours lecture in uni
Very good video. Perfect explanation. Thank you.
Glad it was helpful!
thanks for your videos man, sometimes what i really want is someone to explain this stuff from another angle in an intuitive and clear way like this
it's a great idea that you walk into the video. this way we can take a screen shot of the notes. also, if you do write anything on the board, throughout the video, then may be you can walk out of the camera view at the end. that might be really helpful. thanks
Great work! Never thought I would understand the concept of SVM by just watching one video. 👍🏼 Hope more people watch and subscribe.
Amazing video! Very well explained. Thank you for your work!
CLEAR EXPLAINATION THANK YOU.
Ur explanation for SVM is impeccable! Thanks a lot for the video :) You've got a new subscriber here
Absolutely amazing, as always
Very helpful lecture
You're such a good teacher! Thank you so much this is really helpful..
wooooo! Amazing man. Thank you for this education. You made it extremely easy to understand.
Tremendous explanation thank you!
Thanks Ritvik for awesome explanation.
So so helpful. Thanks so much Ritvik
Awesome! Thank you!
extremely clear lecture. wonderful
this is such a fantastic video. thank you so much for explaining things so well!
can you make a video explaining Baum-Welch
In your second figure, is the margin not defined as the distance between the decision boundary and the support vectors? So the distance you're illustrating is 2x margin? Other than that your videos are amazing. Thanks
Looking forward to math video
Great explanation. Thanks!
awesome
very clear explanation，thank you！
Awsome Video
What a great lecture!
@1:34 "...people who don't know about statistics or anything at all..." (ears perk up)
excelent
Thank you- very well explained!
You are amazing!!!
You are amazing! Thank you!
You are!
amazing 👏
Thanks!
best videos of ML on youtube
Very intuitive
Damn easy to understand now. Tks
Good work!
this is so amazing and simple to grab
thanks!
@@ritvikmath , Thank you for the video. Generally outliers are removed before applying the algorithm, then still why outliers are used while considering the disadvantage of algorithm?
Very helpful, thank you
Can we use SVM? If we want to analyze repeated event (example sheetbreak, etc which happen once 1 month ) by reading historical data and give labels, 1 hour before break, 2 hours before break 3 hours before break up to 8 hours before break? . then we can do something to prevent that event, before it really hapenned
What the best algorithm for this case if SVM is not suitable?
Thankyou
amazing work! Very helpful... thanks a lot!
You're amazing this video has helped so much. Thank you!!
really good tutation go on
this guy is fantastic
Underrated!!
Great content, as always!
hats off, you got one more subscriber
youuuuuuuuuuu areeeee the bessstttttt i sweaaaaaar 🤩👏
As always making it look simples !
Will you focus on classification or also touch regression ?
Looking forward for the next video !
ela
man, you are great. thank youuu❤❤
very clear! thanks
You're welcome!
thank you
Welcome!
thank you!
Thanks❤🌹🎈
awesome!!!
Hey Can you do a video on Post-double selection lasso please
great content!
why isn't this guy teaching in some of the top schools in the US ?
Dummy comment for this awesome channel to get algorithm support and hit more subs
love it!
Good contents thanks!
thanks
What I find confusing is how only the support vectors are needed to determine the decision boundary. Surely you want your decision boundary to be dependent on all data points.
Because you’re trying to maximize the boundary, points not defining the boundary don’t need to be considered. Think of it like. If you were to remove that data point, would the boundary change?