Everyone watching this video lectures knows how the quality of the lecture is.. It's speechless and crystal clear I can say. Thanks MIT and prof Alexander Amini 👌
Your lecture is very fine awesome and great ,I want to follows it again again ,your speech ,the words and the other things are awesome ,the way of presentation is very good ,you are looking awesome 😀 followable, Regards God blesse you ,want to keep in touch with you ,can I have mail id, whatapp number,
Hi social person well said. In time 11:20 I have the self image of deep learning is able to learn to brain waves the self perfect waves wen you love ou dye. make the feel good in a dark place. So it learn only good things to do for us humans. Water air dirt and water! Fire is optional
..and from Morocco please, I mean from Africa and for free! Thanx MIT and to you Sir. Alexander for such great opportunity. may the great soul bless you all on this lecture! stay safe everyone!!
@G V being physically present there, the students studying with you and the lab work are a big part of the learning, and not something that's replicated by these youtube vids
I've tried so many courses so far on deep learning but could only pick up bits and pieces from the way they were delivered/the quality of the content. Even the so called giants in the tech industry offering an AI courses was horrible. But, this!!! I've only gone through lecture 1 so far and i already feel so comfortable with the pace, and the way the concepts are put across. That's why an MIT education is unparalleled and MIT's OpenCourseware is just an absolute gem of an initiative. Thank you Prof Amini for putting this up and giving us a chance to learn as well!
The cleanest and tightest deep learning intro lecture I've ever come across. Most others either get lost in the theory and math or in the coding. Skipping the coding using pseudo code and displaying the math along with the diagrams was really helpful.
Thank you for your professional lecture! To be honest, my mom is an AI expert with years of dedicated experience in Machine Learning and Deep Learning. As a software engineer, I wanted to have some knowledge of Deep Learning in recent days. One day I asked my mom via email. She instantly recommended me to join your course in UA-cam. Now watching your videos becomes an important part of my daily life. I'm really happy to learn a lot from your lectures.
I've only recently taken a real interest in deep learning, and this by far is one of the clearest lectures I have ever seen in any field of similar complexity
41:48 To minimize confusion: He misspoke here. SGD is not the 'vanilla gradient descent' algorithm he just demoed. SGD stands for 'stochastic gradient descent'. Is the basis for all the other algorithms in the shown list. In that regard it is 'vanilla'. However, it is true that it has a fixed learning rate. - He explains the difference later at 44:00.
30:12 The definition of cross entropy loss function should have a negation around the whole right-hand-side, i.e., J(W) = - (1/n sigma ... ). So the resulting value will be positive, just like most shannon-entropy-related things would be defined.
THANK GOD I FOUND THIS COURSE. thank you so much! great lecture, so clear. Cant believe all the new information i just learned in a 50 minute video. EVERY MINUTE was perfected to best quality. THANK YOU SO MUCH.
Golden, diamond, all the best thing is converted into knownledge. It's really my privilege here to be able to watch a recent MIT course, eventually in 2020. I'm following ML field, and you just make me feel so happy and motivated to move forwards. All these knownledge are truly golden. Thank you so much.
@@AAmini You are absolutely the best Sir. I was looking to get into deep learning from web development bc how long can one make web stuff and this is amazing. Definetely going to follow the course. I'd be obliged if you were to post some aditional reading materials..
Bro can you help me ...I am able to understand the concepts whole idea but ...what I am missing is code in tf can you help from where to learn I know basics of python
I'm an engineering student and was really searching for some good stuff related to deep learning for my final year project...feeling awesome to have the latest lectures from such a prestigious institution. Thanks to you Sir.
Dear Prof. Amini, deeply impressed by the quality of content and delivery of your lecture. Feel privileged to listen to such a dedicated teacher and scientist.
This lecture is really clear and easy to follow. Except there are a couple of mistakes on the slides that make it a bit harder. First, at 23:00, I think the second equation should have g(z_j) not just z_j. That is, the activation function is applied as shown in the figure so the y's are sums over g(z_j) with weights w2. Second, the cross entropy equation at 30:00 should have a minus sign out in front of the whole right-hand-side of the equation, so the loss is positive, just like the squared error loss for the regression problem on the next slide. Entropy is always sum over -p ln(p), with a minus out front, since p
One of the amazing thing I have found on UA-cam. It is free and we can never thank you for this. I am pleased to see everything I wish is here and I wish we could have this kind of education in our country but this is great. Prof Alexander Amini you are great. Thank You so much.
You know you're at a top class teaching and research institution when the guy says "this is a formulation introduced by Claude Shannon, _here_ at MIT..."
This is seriously excellent: Such clear & concise explanations to a complicated topic. The slides were also very useful. I honestly can't imagine it being better delivered. After continuously coming back and forth to this subject I'd say this is the best foundational material I have seen on the topic and ultimately a solid basis reference.
What a genuinely brilliant teacher and fantastic person. I'll be watching this to aid my Honours thesis. Thank you kindly for making this fantastic information publicly available, I am extremely grateful. It inspires me to do the same!
undoubtedly one of the best and most effective presentation for an introduction to a complex subject like Deep-Learning, available on youtube for free viewing and learning. Kudos and best wishes Alexander.
Happened to hit this lecture while browsing, But I couldn't resist watching it till the end and subscribing the channel as well. By far the best lecture I have came across on DL, lucky to have this much quality MIT content on youtube for free !
Although I am authorized to give lectures on data science and deep learning myself and work self-employed in this field, the precision and clarity of the course is phenomenal. I am very grateful to live in a time where you can consult MIT's courses online for free and be inspired by its great professors. Many thanks for doing this sent from Germany!
I'm glad you're being sponsored by Lambda Labs. The Lambda Stack is the best way to get Tensorflow running on Linux. Thank you, Stephen Balaban. You rock!
Hi Alexander nice too see your videos, I'm writing from Ecuador, South America, thank you so much because I've been waiting to learn deep learning since last year but I didn't know how starterd
currently studying my master's degree in computer science the UK with a speciality in AI, in fact, my dissertation is in artificially intelligent autonomous vehicular research and I must say that these lectures are amazing.
oh my goodness!! I feel like I didn't know anything about it when i have actually implemented a few solutions with NLP & images. Loved every bit of it. Thank you for the great knowledge and presentation. Subscribed.
I am surprised by myself that I understood each and every word of this lecture. I really can't express how it feels. Thanks Prof Alexander Amini and MIT for sharing this lecture series.
I just cant understand how you dislike this video. I mean, it is uploaded just for the pure sake of education and it is one of the top lectures of its field if not the best...
There is a typo at 23:18 where the z outputs need to be nonlinearized before summing up into output layers. The diagram shows this but the equation doesn't. :D
One of the best Deep Learning lectures .... wish we could have labs instructions too... This course is a really fascinating first time im hearing about it
This video should also be a part of ' Introduction to Teaching' class and be mandatory for many professors so that they can learn how to teach. Thank you very much for sharing.
i'm fascinated by deep AI! Actually, i had worked in a personal art project where using applied AI, i created characters from paintings and barbie dolls. i wish to do more, like compile a github repository on my own and test them out. Especially the paper on NeRF, i want to try that out myself! And so, here i am trying to learn the basics of deep learning to get a solid head start. So thank you for this lecture series~
Go on their website, and see the requirements for bachelors or masters degree. Also, go to Edx.org, there you can take courses from MIT and if you do well in them , you can strengthen your application
if I found this early, I think I could be able to conduct the application of CNN in my course project which is about the "Age-invariant face recognition".And I really enjoy this lecture.
Fascinating, brilliant! Though deep learning is far away from my knowledge or academic background, your lecture is cristal clear and opens a door for me. Thank you!
at first i thought i would just get bored but i am really surprised that i didnt come to know when i reached the end of the video,the video is really interesting and teacher is really amazing..will watch more videos of this course.Looking forward to the coure videos ahead.
I have gone thru' various video on Deep Learning and found it very difficult to understand. Most of teachers try to explain in mathematical language and make it more complex for a beginner to understand. You nailed it, Alexander. Terrific explanation. The pace and quality of your teaching is truly fantastic. Request you to provide a detailed course of Deep Learning. Thank you.
Everyone watching this video lectures knows how the quality of the lecture is.. It's speechless and crystal clear I can say. Thanks MIT and prof Alexander Amini 👌
Thank you very much!
Your lecture is very fine awesome and great ,I want to follows it again again ,your speech ,the words and the other things are awesome ,the way of presentation is very good ,you are looking awesome 😀 followable,
Regards
God blesse you ,want to keep in touch with you ,can I have mail id, whatapp number,
@@AAmini Are you going to create a course with hands on coding on tensorflow?
Hi social person well said. In time 11:20 I have the self image of deep learning is able to learn to brain waves the self perfect waves wen you love ou dye.
make the feel good in a dark place. So it learn only good things to do for us humans. Water air dirt and water! Fire is optional
Alexander Amini it’s a great work you did. I didn’t think I would be able to understand this type of lectures but I did.
Imagine being in 2020 and having the privilege to watch a fresh/recent MIT course at your sofa, damn
..and from Morocco please, I mean from Africa and for free! Thanx MIT and to you Sir. Alexander for such great opportunity. may the great soul bless you all on this lecture! stay safe everyone!!
טטט
without spending a $
@G V being physically present there, the students studying with you and the lab work are a big part of the learning, and not something that's replicated by these youtube vids
@@somilmishra9192 yeah but at least it is a taste of it all.
I've tried so many courses so far on deep learning but could only pick up bits and pieces from the way they were delivered/the quality of the content. Even the so called giants in the tech industry offering an AI courses was horrible. But, this!!! I've only gone through lecture 1 so far and i already feel so comfortable with the pace, and the way the concepts are put across. That's why an MIT education is unparalleled and MIT's OpenCourseware is just an absolute gem of an initiative. Thank you Prof Amini for putting this up and giving us a chance to learn as well!
The cleanest and tightest deep learning intro lecture I've ever come across. Most others either get lost in the theory and math or in the coding. Skipping the coding using pseudo code and displaying the math along with the diagrams was really helpful.
Thank you for your professional lecture!
To be honest, my mom is an AI expert with years of dedicated experience in Machine Learning and Deep Learning. As a software engineer, I wanted to have some knowledge of Deep Learning in recent days. One day I asked my mom via email. She instantly recommended me to join your course in UA-cam. Now watching your videos becomes an important part of my daily life. I'm really happy to learn a lot from your lectures.
You are so lucky
That's the reason why everyone want to study at MIT! The teaching quality is outstanding, you can hardly get this experience from any other colleges!
value=True
I've only recently taken a real interest in deep learning, and this by far is one of the clearest lectures I have ever seen in any field of similar complexity
41:48 To minimize confusion: He misspoke here. SGD is not the 'vanilla gradient descent' algorithm he just demoed. SGD stands for 'stochastic gradient descent'. Is the basis for all the other algorithms in the shown list. In that regard it is 'vanilla'. However, it is true that it has a fixed learning rate. - He explains the difference later at 44:00.
30:12 The definition of cross entropy loss function should have a negation around the whole right-hand-side, i.e., J(W) = - (1/n sigma ... ).
So the resulting value will be positive, just like most shannon-entropy-related things would be defined.
I noticed that too. I think you are correct and looking at other sources, there is always a minus sign out front.
THANK GOD I FOUND THIS COURSE. thank you so much! great lecture, so clear. Cant believe all the new information i just learned in a 50 minute video. EVERY MINUTE was perfected to best quality. THANK YOU SO MUCH.
This is why every student strives to get to the best institutions. The quality of teaching is just too great.
Exactly! The flow is so nice and engaging. Every word imparts knowledge. Everyone needs a mentor like him I believe to mould their personality.
MIT's commitment to making knowledge truly "open" is commendable ... have been seeing this from the OCW days.
At 32:17 it says remember W contains the bias W^0 but it didn't because the size (1 to m) had to match that of the input! See W being defined at 12:43
Golden, diamond, all the best thing is converted into knownledge. It's really my privilege here to be able to watch a recent MIT course, eventually in 2020. I'm following ML field, and you just make me feel so happy and motivated to move forwards. All these knownledge are truly golden. Thank you so much.
I would like to say thank to Mr Alexander Amini and his team for sharing comprehensive knowledge about Deep learning.
Man, these concepts are said in plain english, but so effectively. Even in a few sentences I feel like I learn so much. Fantastic quality
Quality Course. I have been learning about deep learning from various courses and books. This course helps piece things together...its amazing
Finally, I could find a great lecture for ML! Many thanks, Dr. Amini, for such an incredible lecture.
Hey, did you downloaded all the slides of these lectures. Actually, they are being ready for 2022 class. So, I couldn't find them online
Thanks so much. People from around the world are watching and learning.
One of the best Deep Learning lectures .... wish we could have labs instructions too...
Thanks! All lab instructions that we presented during class are also available on the course Github page (linked from the class website)
Alexander Amini are u Persian ?
@@AAmini You are absolutely the best Sir. I was looking to get into deep learning from web development bc how long can one make web stuff and this is amazing. Definetely going to follow the course. I'd be obliged if you were to post some aditional reading materials..
Bro can you help me ...I am able to understand the concepts whole idea but ...what I am missing is code in tf can you help from where to learn I know basics of python
Muzamil Hussain google
I'm an engineering student and was really searching for some good stuff related to deep learning for my final year project...feeling awesome to have the latest lectures from such a prestigious institution. Thanks to you Sir.
Dear Prof. Amini, deeply impressed by the quality of content and delivery of your lecture. Feel privileged to listen to such a dedicated teacher and scientist.
This lecture is really clear and easy to follow. Except there are a couple of mistakes on the slides that make it a bit harder. First, at 23:00, I think the second equation should have g(z_j) not just z_j. That is, the activation function is applied as shown in the figure so the y's are sums over g(z_j) with weights w2. Second, the cross entropy equation at 30:00 should have a minus sign out in front of the whole right-hand-side of the equation, so the loss is positive, just like the squared error loss for the regression problem on the next slide. Entropy is always sum over -p ln(p), with a minus out front, since p
The first error is fixed on the downloadable slides (slide 33).
Just a tip: Watch the lecture a second time, you'll pick up stuff that you missed the first time
Three times for me... too much math concepts to understand.
Manuel Fuentes doesn’t matter. you’re in the process, keep at it!
Should an undergrad pursue masters in deep learning of do online course ?
@@akshatbhatt5384 no
my dumb butt has to watch it more than twice
One of the amazing thing I have found on UA-cam. It is free and we can never thank you for this. I am pleased to see everything I wish is here and I wish we could have this kind of education in our country but this is great. Prof Alexander Amini you are great. Thank You so much.
You know you're at a top class teaching and research institution when the guy says "this is a formulation introduced by Claude Shannon, _here_ at MIT..."
not only was I aware of it, that's a cool notice
Same as how I felt when I was on exchange at UC Berkeley and saw the parking lots reserved for Nobel laureates.
This is seriously excellent: Such clear & concise explanations to a complicated topic. The slides were also very useful. I honestly can't imagine it being better delivered. After continuously coming back and forth to this subject I'd say this is the best foundational material I have seen on the topic and ultimately a solid basis reference.
I hope all my classes can be this organized and well-informative
15:15 Non linearities
33:33 Loss Optimization
37:37 Back Propagation
What a genuinely brilliant teacher and fantastic person. I'll be watching this to aid my Honours thesis. Thank you kindly for making this fantastic information publicly available, I am extremely grateful. It inspires me to do the same!
undoubtedly one of the best and most effective presentation for an introduction to a complex subject like Deep-Learning, available on youtube for free viewing and learning. Kudos and best wishes Alexander.
I would say that I'm surprised of how well Alexander taught this lesson ,I'll definitely watch the rest of the course.
Happened to hit this lecture while browsing, But I couldn't resist watching it till the end and subscribing the channel as well. By far the best lecture I have came across on DL, lucky to have this much quality MIT content on youtube for free !
very clear, no unnecessary beating around the bush. Loved it.
Wonderful explanation about the process of convolution, the steps of a CNN, and the most common applications! Thank you very much!
Excellent job! Thanks Aleander Amini and his MIT team for such comprehensive but impressively clear introduciton to deep learing.
My God!! By far the best introductory video about Deep Learning. I really hope the rest of the course is also so informative. Thank you very much
He is only 24! This guys's gonna rock!
Holy shit.
@@GreenGoblinCoryintheHouse My exact reaction also!
He looks really good for someone that is 620448401733239439360000.
Thanks Alexander for great community services. Best deep learning lecturers
Thanks a lot for taking the time to put this up on UA-cam, this really helps me
What a time to be alive! Thanks MIT and thanks Alexander.
This lecture was just "MIND BLOWING", I mean its the best course I have ever seen !!! Thank you so much MIT and professor Alexander Amini ...
Although I am authorized to give lectures on data science and deep learning myself and work self-employed in this field, the precision and clarity of the course is phenomenal.
I am very grateful to live in a time where you can consult MIT's courses online for free and be inspired by its great professors.
Many thanks for doing this sent from Germany!
The color coding in back propagation part really helped.
One of the best online resources for Machine Learning. Whole hearted thanks to MIT and the teaching team.
This is the best class and explanation of Deep Learning I've ever seen. All is clear, awesome!
I'm glad you're being sponsored by Lambda Labs. The Lambda Stack is the best way to get Tensorflow running on Linux. Thank you, Stephen Balaban. You rock!
so far the best lecture about deep learning i have ever seen.
It's explaining everything about deep learning from its root, all those equations become much more easily to understand. Thank you very much!
man, at 25 yoa? unbelievable. Keep it up Sasha! and thank you for incredible lectures
Much awaited Lecture series... 2019 lectures were amazing...BIG thank you.
Im siting in a small village and watching /learning from the best in world. Woah !! I love internet. Thanks to covid this lecture series is free.
Thanks to Covud Really ?
@@mihirnatani4479 Yes Covid is a big fraud don't you still know it.
Hi Alexander nice too see your videos, I'm writing from Ecuador, South America, thank you so much because I've been waiting to learn deep learning since last year but I didn't know how starterd
Thanks for sharing this incredible course online! Very clear to understand. Thanks to Alexander Amini and MIT!
currently studying my master's degree in computer science the UK with a speciality in AI, in fact, my dissertation is in artificially intelligent autonomous vehicular research and I must say that these lectures are amazing.
Great intro. You made neural networks (and the math behind them) really easy to understand.
oh my goodness!! I feel like I didn't know anything about it when i have actually implemented a few solutions with NLP & images. Loved every bit of it. Thank you for the great knowledge and presentation.
Subscribed.
Thanx for sharing knowledge it really helps to understand DL lots of love from INDIA
alexender sir u deserve a standing ovation
I am surprised by myself that I understood each and every word of this lecture. I really can't express how it feels. Thanks Prof Alexander Amini and MIT for sharing this lecture series.
Thanks for sharing comprehensive knowledge about Deep learning.
Really happy for getting an opportunity to learn an MIT Deep Learning course. The excellent and precise way of teaching.
Thank god UA-cam exists and people like Alexander
It is an informative presentation . It is the MITian's code of professionalism . Thank you
Excellent introduction to DNN! You should upload more videos on this topic. It helped me a lot to understand the big picture of the system. Thanks.
A great primer to all basic concepts like Perceptrons, Gradients, Propagation, Regularization, etc. Must watch for a beginner.
Best material! , Thank you for amazing explanation of this complex subject.
Much awaited Lecture series... 2019 lectures were amazing...BIG thank you.
This course is a really fascinating first time im hearing about it
I just cant understand how you dislike this video. I mean, it is uploaded just for the pure sake of education and it is one of the top lectures of its field if not the best...
I cannot understand why it hurts if someone dislikes what you like. Stop judging others and live for yourself jerk.
@@mangalpandey4635 You're judging others right now, jerk
this video saved my life
How?
Metaphorically speaking ... i had a university assignment regarding DL and this video was very very helpful to me
There is a typo at 23:18 where the z outputs need to be nonlinearized before summing up into output layers. The diagram shows this but the equation doesn't. :D
One of the best Deep Learning lectures .... wish we could have labs instructions too...
This course is a really fascinating first time im hearing about it
This video should also be a part of ' Introduction to Teaching' class and be mandatory for many professors so that they can learn how to teach. Thank you very much for sharing.
Thanks a lot Alex. Your lecture is so good. Especially how you explain the back propagation, it is very clear.
I never understood it so better before. Thanks for posting it.
i'm fascinated by deep AI! Actually, i had worked in a personal art project where using applied AI, i created characters from paintings and barbie dolls. i wish to do more, like compile a github repository on my own and test them out. Especially the paper on NeRF, i want to try that out myself! And so, here i am trying to learn the basics of deep learning to get a solid head start. So thank you for this lecture series~
I'm taking a Machine Learning concentration at Carnegie Mellon University and these lectures will be of so much help. Thank you!👏👏👏
Thank you for sharing your entire lecture series most universities are not this generous. Amazing
Amazing! I am speechless after watching this video.
I am from a third world country, How can I get to study at MIT is incredible how well he explained how deep learning works.
Go on their website, and see the requirements for bachelors or masters degree.
Also, go to Edx.org, there you can take courses from MIT and if you do well in them , you can strengthen your application
Really enjoyed the series especially the "Limitations and looking forward" lecture. Looking forward to the guest lectures.
It honored to me learn from MIT. I thanks to MIT and especially honorable teacher.
You are incredible and I really proud to see that you are originally from Iran (love you guys) and best wishes :*
awesome.. I can learn about the neural networks from MIT. just sit and stay tune the channel. clearly done the presentation....
it's an informative lecture and clear introduction, it's pulling you to watch it.
thank you, prof. Alexander
thanks to the technology and internet, we able to absorb the knowledge from anywhere
if I found this early, I think I could be able to conduct the application of CNN in my course project which is about the "Age-invariant face recognition".And I really enjoy this lecture.
Very clear and easy to understand lectures, bravo prof Alexander Amini
Great speaker and concise and easy to understand lecture slides!!
wow man! I was really surprised that I could grab everything you explained!
Thanks a lot for the best lectures on Deep Learning...
Fascinating, brilliant! Though deep learning is far away from my knowledge or academic background, your lecture is cristal clear and opens a door for me. Thank you!
at first i thought i would just get bored but i am really surprised that i didnt come to know when i reached the end of the video,the video is really interesting and teacher is really amazing..will watch more videos of this course.Looking forward to the coure videos ahead.
Definitely the best lecture on deep learning intro !
WOW I am getting more and more interested in Deep learning, thanks for such a great course
The best lecture. Period.
Nice lecture. I learnt so much from this 1hr video than thru reading or other courses. Hoping to follow these video judiciously😀
I have gone thru' various video on Deep Learning and found it very difficult to understand. Most of teachers try to explain in mathematical language and make it more complex for a beginner to understand. You nailed it, Alexander. Terrific explanation. The pace and quality of your teaching is truly fantastic. Request you to provide a detailed course of Deep Learning. Thank you.
Cool, just got interested in playing around with TensorFlow 2.0 and now UA-cam recommends this video. Perfect!
Amazing! This is really a gift to humanity, freeing such amazing content for free.
This is the best lecture on Deep Learning I have ever seen