51:52 Position Encoding - isn't this just the same as giving everything a number/timestep? but with a different name (order,sequence,time,etc) ,so we're still kinda stuck with discrete steps. If everything is coded by position in a stream of data wont parts at the end of the stream be further and further away in a space from the beginning. So if a long sentence started with a pronoun but then ended with a noun the pronoun representing the noun would be harder and harder to relate the two: 'it woke me early this morning, time to walk the cat'
@DreamBuilders-rq6km5 годин тому
Thanks for sharing this knowledge. Be blessed
@AmarVashishth6 годин тому
Attended Deep Learning lectures at a topmost college of a country, here he clearly explained all that in a single lecture for which the former took 10s of lectures to explain.
@husseinekeita89097 годин тому
Thank you for sharing quality content like this for free for several years
@4threich1667 годин тому
Where is the software lab?
@sheevys8 годин тому
Interesting view regarding the kolomogorov Arnold representation. His buddies at MIT just released KAN paper, I wonder how this idea evolves.
@htoorutube10 годин тому
Software Lab 1 still not made available, when will that happen?
@jorgeguiragossian848810 годин тому
Have any of the labs been published yet?
@maithriashokan12 годин тому
I loved this session! I am getting interested in it.
@waqarahmed731914 годин тому
is this course taught to mit students as well? or is it just like an online? I liked the course but i wish there were readings attached with it, which went into the mathematical details.
@woodworkingaspirations172016 годин тому
Waiting patiently
@AshokKumar-mg1wx7 годин тому
That's the spirit
@dr.smahanif802716 годин тому
just WOW! You almost summarize my learning of 4 years PhD in 1 hour. Keep it up dear. You have everything to speculate your expertise :)
@samiragh6316 годин тому
Cant wait...
@ayanah482121 годину тому
I really appreciate you posting this material!! Thank you 🙏
@wetss291422 години тому
и9им9ииои9о9ии9
@shahriarahmadfahim6457День тому
But the lab between Lecture 2 and 3 is still not published in the website?
@benjaminy.9 годин тому
I think it is not their practice to publish their lab work
@genkideska4486День тому
Waiting ..
@gmemon786День тому
Great lecture, thank you! When will the labs be available?
@ps33012 дні тому
Is there any similar lessons on liquid neural network with some real number calculation ?
@user-tb8yi9dk9f2 дні тому
When lab code will be released?
@TheViral_fyp3 дні тому
Wow great 👍 job buddy i wanna your book suggestion for DSA!
@abdulbasitnisar3 дні тому
Please can anyone tell me, i am beginner and self learning these, can i do it or its too advance???!
@ayanah48213 дні тому
Omg everything makes sense! Your explanations were so simple and easy to understand 😭🙏
@pedrojesusrangelgil50643 дні тому
I'm a beginner in ml and ai fields and it's amazing to have these lectures online and free. I've a doubt: the neural network showed in 33:44 shouldn't be named 'multi' layer rather than 'single' layer neural network since it has an output layer separated of the hidden layer? Thanks!
@SandeepPawar13 дні тому
Fantastic 🎉 thank you
@gemini_5374 дні тому
Gemini: This lecture is about reinforcement learning, a type of machine learning where an agent learns through trial and error. The lecture starts with comparing reinforcement learning with other learning paradigms. Reinforcement learning is different from supervised learning where the agent is given labeled data. It is also different from unsupervised learning where the agent is only given unlabeled data. In reinforcement learning, the agent is given rewards for taking desired actions. The core idea of reinforcement learning is to learn a policy, which is a function that maps states to actions. The agent tries to learn a policy that maximizes the total reward it gets over time. There are two main approaches to reinforcement learning: Q-learning and policy learning. Q-learning focuses on learning a Q-function, which estimates the expected future reward for taking a particular action in a particular state. Policy learning focuses on directly learning a policy that maps states to actions. The lecture also talks about deep reinforcement learning, which combines reinforcement learning with deep learning. Deep learning allows reinforcement learning algorithms to learn complex policies from high-dimensional data. One example of deep reinforcement learning is AlphaStar, a program developed by DeepMind that can defeat professional human players in the real-time strategy game StarCraft II.
@PanZheng4 дні тому
too bad, even MIT courseware gives a false definition of AI in the slide 7:40
@abdulbasitnisar4 дні тому
Can absolute beginners follow these lectures???
@hamzawaheed26434 дні тому
amazing video
@enisten4 дні тому
How do you predict the first word? Can you only start predicting after the first word has come in? Or can you assume a zero input to predict the first word?
@vaibhavverma68134 дні тому
The mathematics which I studied this semester is completely making sense now.
@giovannimurru5 днів тому
Great lecture as always! Can’t wait to start the software labs. Just curious why isn’t the website served over https? Is there any particular reason?
@rahulprasad61165 днів тому
Explained so well, hopefully I will get more video to watch.... Can somebody suggest me to find best free material (video) like this video for AI, I desperately want to make my career in field of data science and AI
@shahriarahmadfahim64575 днів тому
Can't believe how amazingly the two lecturers squeeze so much content and explain with such clarity in an hour! Would be great if you published the lab with the preceding lecture coz the lecture ended setting up the mood for the lab haha. But not complaining, thanks again for such amazing stuffs!
@mohamedbille10675 днів тому
good Presentation agood overview about deep learning thanks sir Alexander Amini
@arpanpradhan4935 днів тому
You are a great teacher. I wish my professor explained this way. 🎉
@wendywu53595 днів тому
Love your style!
@01_abhijeet495 днів тому
Miss was stressed if she made the presentation complex
@lucasgandara41755 днів тому
Is Lex up for another participation as lecturer ? Is he still working on this topic? He's such a great speaker.
@stephenlii17445 днів тому
Mark it, learn later
@turhancan976 днів тому
Initially, N-gram statistical models were commonly used for language processing. This was followed by vanilla neural networks, which were popular but not enough. The popularity then shifted to RNN and its variants, despite their own limitations discussed in the video. Currently, the transformer architecture is in use and has made a significant impact. This is evident in applications such as ChatGPT, Gemini, and other Language Models. I look forward to seeing more advanced models and their applications in the future.
@abdelazizeabdullahelsouday81186 днів тому
Was waiting for it from the last one last week, Amazing ! Please i have send you an email asking for some quires, could you let me know how can i get the answers or if there is any channel to connect? thanks in advance
@victortg06 днів тому
This was an extraordinary explanation of Transformers!
@pw72256 днів тому
Ava is such a talented teacher. (And Alex, too, of course.)
@shivangsingh6036 днів тому
That was explained very well! Thanks a lot Ava
@roxymigurdia16 днів тому
thanks daddy
@frankhofmann58196 днів тому
I now feel like a fully connected neural network bye myself now because I've watched hundreds of videos at night that concern deep learning. Best regards from Berlin!
@frankhofmann58197 днів тому
I'm sitting here in wonderful Berlin at the beginning of May and looking at this incredibly clear presentation! Wunderbar! And thank you very much for the clarity of your logic!
@wqesdc83397 днів тому
Amazing for free lectures ❤
@jessenyokabi42907 днів тому
Another extraordinary lecture FULL of refreshing insights. Thank you, Alex and Ava.