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!
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!
*Abstract* This lecture delves into the realm of sequence modeling, exploring how neural networks can effectively handle sequential data like text, audio, and time series. Beginning with the limitations of traditional feedforward models, the lecture introduces Recurrent Neural Networks (RNNs) and their ability to capture temporal dependencies through the concept of "state." The inner workings of RNNs, including their mathematical formulation and training using backpropagation through time, are explained. However, RNNs face challenges such as vanishing gradients and limited memory capacity. To address these limitations, Long Short-Term Memory (LSTM) networks with gating mechanisms are presented. The lecture further explores the powerful concept of "attention," which allows networks to focus on the most relevant parts of an input sequence. Self-attention and its role in Transformer architectures like GPT are discussed, highlighting their impact on natural language processing and other domains. The lecture concludes by emphasizing the versatility of attention mechanisms and their applications beyond text data, including biology and computer vision. *Sequence Modeling and Recurrent Neural Networks* - 0:01: This lecture introduces sequence modeling, a class of problems involving sequential data like audio, text, and time series. - 1:32: Predicting the trajectory of a moving ball exemplifies the concept of sequence modeling, where past information aids in predicting future states. - 2:42: Diverse applications of sequence modeling are discussed, spanning natural language processing, finance, and biology. *Neurons with Recurrence* - 5:30: The lecture delves into how neural networks can handle sequential data. - 6:26: Building upon the concept of perceptrons, the idea of recurrent neural networks (RNNs) is introduced. - 7:48: RNNs address the limitations of traditional feedforward models by incorporating a "state" that captures information from previous time steps, allowing the network to model temporal dependencies. - 10:07: The concept of "state" in RNNs is elaborated upon, representing the network's memory of past inputs. - 12:23: RNNs are presented as a foundational framework for sequence modeling tasks. *Recurrent Neural Networks* - 12:53: The mathematical formulation of RNNs is explained, highlighting the recurrent relation that updates the state at each time step based on the current input and previous state. - 14:11: The process of "unrolling" an RNN is illustrated, demonstrating how the network processes a sequence step-by-step. - 17:17: Visualizing RNNs as unrolled networks across time steps aids in understanding their operation. - 19:55: Implementing RNNs from scratch using TensorFlow is briefly discussed, showing how the core computations translate into code. *Design Criteria for Sequential Modeling* - 22:45: The lecture outlines key design criteria for effective sequence modeling, emphasizing the need for handling variable sequence lengths, maintaining memory, preserving order, and learning conserved parameters. - 24:28: The task of next-word prediction is used as a concrete example to illustrate the challenges and considerations involved in sequence modeling. - 25:56: The concept of "embedding" is introduced, which involves transforming language into numerical representations that neural networks can process. - 28:42: The challenge of long-term dependencies in sequence modeling is discussed, highlighting the need for networks to retain information from earlier time steps. *Backpropagation Through Time* - 31:51: The lecture explains how RNNs are trained using backpropagation through time (BPTT), which involves backpropagating gradients through both the network layers and time steps. - 33:41: Potential issues with BPTT, such as exploding and vanishing gradients, are discussed, along with strategies to mitigate them. *Long Short Term Memory (LSTM)* - 37:21: To address the limitations of standard RNNs, Long Short-Term Memory (LSTM) networks are introduced. - 37:35: LSTMs employ "gating" mechanisms that allow the network to selectively retain or discard information, enhancing its ability to handle long-term dependencies. *RNN Applications* - 40:03: Various applications of RNNs are explored, including music generation and sentiment classification. - 40:16: The lecture showcases a musical piece generated by an RNN trained on classical music. *Attention Fundamentals* - 44:00: The limitations of RNNs, such as limited memory capacity and computational inefficiency, motivate the exploration of alternative architectures. - 46:50: The concept of "attention" is introduced as a powerful mechanism for identifying and focusing on the most relevant parts of an input sequence. *Intuition of Attention* - 48:02: The core idea of attention is to extract the most important features from an input, similar to how humans selectively focus on specific aspects of visual scenes. - 49:18: The relationship between attention and search is illustrated using the analogy of searching for relevant videos on UA-cam. *Learning Attention with Neural Networks* - 51:29: Applying self-attention to sequence modeling is discussed, where the network learns to attend to relevant parts of the input sequence itself. - 52:05: Positional encoding is explained as a way to preserve information about the order of elements in a sequence. - 53:15: The computation of query, key, and value matrices using neural network layers is detailed, forming the basis of the attention mechanism. *Scaling Attention and Applications* - 57:46: The concept of attention heads is introduced, where multiple attention mechanisms can be combined to capture different aspects of the input. - 58:38: Attention serves as the foundational building block for Transformer architectures, which have achieved remarkable success in various domains, including natural language processing with models like GPT. - 59:13: The broad applicability of attention beyond text data is highlighted, with examples in biology and computer vision. i summarized the transcript with gemini 1.5 pro
@@_KillerRobots I used the following single prompt: Create abstract and summarize the following video transcript as a bullet list. Prepend each bullet point with starting timestamp. Don't show the ending timestamp. Also split the summary into sections and create section titles. `````` create abstract and summary
Mind = Blown. Ava, you're a fantastic teacher. This is the best intuitive + technical explanation of Sequence Modeling, RNNs and Attention on the internet. Period.
excellent video series. Thanks for making them available online! A suggestion when explaining Q, K, V. I would start with a symmetric attention weighting matrix and go on with that at first. Then give an example which shows that the attention is not symmetric, as it is the case between the words "beautiful" and "painting" in the sentence "Alice noticed the beautiful painting". This motivates why we would want to train separate networks for Q and K.
Thanks, it's a great and intense/compact DL overvie, free and open from MIT. Personally, I'd introduce LSTMs a bit later (38 minutes into the 2nd lecture may leave many students behind) and say a bit more how things happened historically (Elman, Schmidhuber, Vaswani).
The first lecture was fairly interesting mainly because we started with an example.. i wish why the RNNs are needed for sequence model can also we explained with a more piratical example .. probably like next word prediction.. i am like 20 minutes into the lecture and feeling completely lost.. i think just too much math can be difficult to to understand user story a/ use case we are trying to solve..
1. Here we are taking "h" as previous history factor or hidden state, is it single dimensional or multidimensional? 2. What is the behavior of "h" - hidden state inside the NN or inside each layer of RNN? (in a single timestamp?) 3. How is mismatch between number of input features and number of out put features is maintained? For example consider image captioning. Here we are giving fixed number of input parameters, but what will determine how many words will be generated as a caption. Or for example consider generation of sentences related to given word, here we are giving one word as input, but what will decide length of output?
When will the labs be available, and how can one have access? It was a great session that improved my knowledge of sequential modeling and introduced me to Self-attention. Thank you, Alex and Ava.
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.
mistake at the slide that appeared at moment (18:38), the last layer is layer t , it is not layer 3 (i.e., ... means that we have alt least one un-appeared one layer ).
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?
Where can we find the software labs material ? As I am eager to implement the concepts practically 🙂 Btw I love these lectures as an ML student .... Thank you 😊
How can we be sure that our predicted output vector will always correspond to a word? There are an infinite number of vectors in any vector space but only a finite number of words in the dictionary. We can always compute the training loss as long as every word is mapped to a vector, but what use is the resulting callibrated model if its predictions will not necessarily correspond to a word?
Dear Alex and Ava, Thank you so much for the insightful sessions on deep learning which are the best I've come across in youtube. I've a query and would appreciate a response from you. In case if we want to translate a sentence from English to French and if we use an encoder decoder transformer architecture, based on the context vector generated from encoder, the decoder predicts the translated word one by one. My question is, for the logits generated by decoder output, does the transformer model provides weightage for all words available in French. For e.g. if we consider that there are N number of words in French, and if softmax function is applied to the logits generated by decoder, does softmax predicts the probability percentage for all those N number of words.
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
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'
Personally, I love the way Ava articulated each word and how she mapped the problem in her head. Great job
These lectures are extremly high quality. Thank you :) for posting them online so that we can learn from one of the best universities in the world.
As I await the commencement of this lecture, I reflect fondly on my past experiences, which have been nothing short of excellent.
Indeed.
Indubitably
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!
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!
Thank you for being the pioneers in teaching Deep Learning to Common folks like me :)
Thank you Alexander and Ava 👍
Can't be waiting for another extraordinary lecture. Thank you Alex and Ava.
This is one of the best and engaging sessions I've ever attended. The entire hour was incredibly smooth, and I was captivated the entire time.
can a 11thgrade student understand this? i mean i tried but i am not able to understand what's going on?
*Abstract*
This lecture delves into the realm of sequence modeling, exploring how neural networks can effectively handle sequential data like text, audio, and time series. Beginning with the limitations of traditional feedforward models, the lecture introduces Recurrent Neural Networks (RNNs) and their ability to capture temporal dependencies through the concept of "state." The inner workings of RNNs, including their mathematical formulation and training using backpropagation through time, are explained. However, RNNs face challenges such as vanishing gradients and limited memory capacity. To address these limitations, Long Short-Term Memory (LSTM) networks with gating mechanisms are presented. The lecture further explores the powerful concept of "attention," which allows networks to focus on the most relevant parts of an input sequence. Self-attention and its role in Transformer architectures like GPT are discussed, highlighting their impact on natural language processing and other domains. The lecture concludes by emphasizing the versatility of attention mechanisms and their applications beyond text data, including biology and computer vision.
*Sequence Modeling and Recurrent Neural Networks*
- 0:01: This lecture introduces sequence modeling, a class of problems involving sequential data like audio, text, and time series.
- 1:32: Predicting the trajectory of a moving ball exemplifies the concept of sequence modeling, where past information aids in predicting future states.
- 2:42: Diverse applications of sequence modeling are discussed, spanning natural language processing, finance, and biology.
*Neurons with Recurrence*
- 5:30: The lecture delves into how neural networks can handle sequential data.
- 6:26: Building upon the concept of perceptrons, the idea of recurrent neural networks (RNNs) is introduced.
- 7:48: RNNs address the limitations of traditional feedforward models by incorporating a "state" that captures information from previous time steps, allowing the network to model temporal dependencies.
- 10:07: The concept of "state" in RNNs is elaborated upon, representing the network's memory of past inputs.
- 12:23: RNNs are presented as a foundational framework for sequence modeling tasks.
*Recurrent Neural Networks*
- 12:53: The mathematical formulation of RNNs is explained, highlighting the recurrent relation that updates the state at each time step based on the current input and previous state.
- 14:11: The process of "unrolling" an RNN is illustrated, demonstrating how the network processes a sequence step-by-step.
- 17:17: Visualizing RNNs as unrolled networks across time steps aids in understanding their operation.
- 19:55: Implementing RNNs from scratch using TensorFlow is briefly discussed, showing how the core computations translate into code.
*Design Criteria for Sequential Modeling*
- 22:45: The lecture outlines key design criteria for effective sequence modeling, emphasizing the need for handling variable sequence lengths, maintaining memory, preserving order, and learning conserved parameters.
- 24:28: The task of next-word prediction is used as a concrete example to illustrate the challenges and considerations involved in sequence modeling.
- 25:56: The concept of "embedding" is introduced, which involves transforming language into numerical representations that neural networks can process.
- 28:42: The challenge of long-term dependencies in sequence modeling is discussed, highlighting the need for networks to retain information from earlier time steps.
*Backpropagation Through Time*
- 31:51: The lecture explains how RNNs are trained using backpropagation through time (BPTT), which involves backpropagating gradients through both the network layers and time steps.
- 33:41: Potential issues with BPTT, such as exploding and vanishing gradients, are discussed, along with strategies to mitigate them.
*Long Short Term Memory (LSTM)*
- 37:21: To address the limitations of standard RNNs, Long Short-Term Memory (LSTM) networks are introduced.
- 37:35: LSTMs employ "gating" mechanisms that allow the network to selectively retain or discard information, enhancing its ability to handle long-term dependencies.
*RNN Applications*
- 40:03: Various applications of RNNs are explored, including music generation and sentiment classification.
- 40:16: The lecture showcases a musical piece generated by an RNN trained on classical music.
*Attention Fundamentals*
- 44:00: The limitations of RNNs, such as limited memory capacity and computational inefficiency, motivate the exploration of alternative architectures.
- 46:50: The concept of "attention" is introduced as a powerful mechanism for identifying and focusing on the most relevant parts of an input sequence.
*Intuition of Attention*
- 48:02: The core idea of attention is to extract the most important features from an input, similar to how humans selectively focus on specific aspects of visual scenes.
- 49:18: The relationship between attention and search is illustrated using the analogy of searching for relevant videos on UA-cam.
*Learning Attention with Neural Networks*
- 51:29: Applying self-attention to sequence modeling is discussed, where the network learns to attend to relevant parts of the input sequence itself.
- 52:05: Positional encoding is explained as a way to preserve information about the order of elements in a sequence.
- 53:15: The computation of query, key, and value matrices using neural network layers is detailed, forming the basis of the attention mechanism.
*Scaling Attention and Applications*
- 57:46: The concept of attention heads is introduced, where multiple attention mechanisms can be combined to capture different aspects of the input.
- 58:38: Attention serves as the foundational building block for Transformer architectures, which have achieved remarkable success in various domains, including natural language processing with models like GPT.
- 59:13: The broad applicability of attention beyond text data is highlighted, with examples in biology and computer vision.
i summarized the transcript with gemini 1.5 pro
Very nice Gemini summary. Single output or chain?
@@_KillerRobots I used the following single prompt: Create abstract and summarize the following video transcript as a bullet list. Prepend each bullet point with starting timestamp. Don't show the ending timestamp. Also split the summary into sections and create section titles.
`````` create abstract and summary
Mind = Blown. Ava, you're a fantastic teacher. This is the best intuitive + technical explanation of Sequence Modeling, RNNs and Attention on the internet. Period.
This was an amazing class and one of the clearest introductions to Sequence Models that I have ever seen. Great work!
Ava is such a talented teacher. (And Alex, too, of course.)
It's a great place to apply all learning strategies for jetpack classes, love it, I just can't wait for more and in depth knowledge.
excellent video series. Thanks for making them available online! A suggestion when explaining Q, K, V. I would start with a symmetric attention weighting matrix and go on with that at first. Then give an example which shows that the attention is not symmetric, as it is the case between the words "beautiful" and "painting" in the sentence "Alice noticed the beautiful painting". This motivates why we would want to train separate networks for Q and K.
excellent way of explaining the deep learning concepts
The intuition building was stellar, really eye opening. Thanks!
Very audible and confidently delivered the lecture perfectly. Thanks
This is not an easy topic to explain but you explained v well and with good presentation skills!
Ojalá todo el mundo fuera así de competente. Da gusto aprender de gente que tiene las ideas claras.
Thanks, it's a great and intense/compact DL overvie, free and open from MIT.
Personally, I'd introduce LSTMs a bit later (38 minutes into the 2nd lecture may leave many students behind) and say a bit more how things happened historically (Elman, Schmidhuber, Vaswani).
thank you so much. the explanation on self-attention is so clearly
This was an extraordinary explanation of Transformers!
The first lecture was fairly interesting mainly because we started with an example.. i wish why the RNNs are needed for sequence model can also we explained with a more piratical example .. probably like next word prediction.. i am like 20 minutes into the lecture and feeling completely lost.. i think just too much math can be difficult to to understand user story a/ use case we are trying to solve..
I am currently studying deep learning and find it very encouraging.
Thank you very much!
Very good lecture. Also perfect timing in respect of my next academic and professional steps.
Great lecture, thank you! When will the labs be available?
Thankyou for uploading the Lectures. Its helpful for students all around the globe.
More complex than the first but brilliantly explained
1. Here we are taking "h" as previous history factor or hidden state, is it single dimensional or multidimensional?
2. What is the behavior of "h" - hidden state inside the NN or inside each layer of RNN? (in a single timestamp?)
3. How is mismatch between number of input features and number of out put features is maintained? For example consider image captioning. Here we are giving fixed number of input parameters, but what will determine how many words will be generated as a caption.
Or for example consider generation of sentences related to given word, here we are giving one word as input, but what will decide length of output?
Thank you for an amazing lecture, easy to follow a complex topic.
Amazing stuff, thanks to every one associated with #AlexanderAmini channel.
One of the best explanations of self attention! It was very intuitive. Thank you so much
When will the labs be available, and how can one have access?
It was a great session that improved my knowledge of sequential modeling and introduced me to Self-attention.
Thank you, Alex and Ava.
Extraordinary explanation and teaching.
Thank you!!
love her energy
been softmaxxing since this one
This is a great summarization of sequence model.
truly amazed at the aura of knowledge.
Thanks for your detailed explanation
That was explained very well! Thanks a lot Ava
Great work guys looking forward to learn more from you guys in succeeding videos.
Thank you for another great lecture, Alexander and Ava !!!
Another extraordinary lecture FULL of refreshing insights.
Thank you, Alex and Ava.
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.
For me to not be a programmer, I did understand her.
what an awesome lecture, thank you!
Hey if possible please upload how you implement this things practically in labs. Theory is important so does practical work
mistake at the slide that appeared at moment (18:38), the last layer is layer t , it is not layer 3 (i.e., ... means that we have alt least one un-appeared one layer ).
Simply superb!
Thank you for your lecture!
Thank you, Ava!
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?
I'm new ai Stu to listen you ❤❤
What a great content
Where can we find the software labs material ? As I am eager to implement the concepts practically 🙂
Btw I love these lectures as an ML student .... Thank you 😊
Plz if you know that let know, thanks in advance
@@abdelazizeabdullahelsouday8118 links in the syllabus, docs.google.com/document/d/1lHCUT_zDLD71Myy_ulfg7jaciCj1A7A3FY_-TFBO5l8/
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?
This was awsome, thank you so much. Does someone knows if the lab or similar excersises are availables as well?
can you please share the Lab session or codes as well to try out?
Wow great 👍 job buddy i wanna your book suggestion for DSA!
How can we be sure that our predicted output vector will always correspond to a word? There are an infinite number of vectors in any vector space but only a finite number of words in the dictionary. We can always compute the training loss as long as every word is mapped to a vector, but what use is the resulting callibrated model if its predictions will not necessarily correspond to a word?
Recurrent neural networks are easier to understand if we understand recursion😁
Brilliant!
Thanks very much
Dear Alex and Ava, Thank you so much for the insightful sessions on deep learning which are the best I've come across in youtube. I've a query and would appreciate a response from you. In case if we want to translate a sentence from English to French and if we use an encoder decoder transformer architecture, based on the context vector generated from encoder, the decoder predicts the translated word one by one. My question is, for the logits generated by decoder output, does the transformer model provides weightage for all words available in French. For e.g. if we consider that there are N number of words in French, and if softmax function is applied to the logits generated by decoder, does softmax predicts the probability percentage for all those N number of words.
Are they sibliings? Alex and Ava?
Is there any similar lessons on liquid neural network with some real number calculation ?
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
Dude, How i'd love to be there sometime.
It’s very much like a partial differential equation isn’t it?
It seems to me that the data comprising the KEY matrix introduces a large external bias on the QUERY matrix, or am I mistaken? thx
excellent so great idris italy
Fantastic 🎉 thank you
very good I like
Once again Ava's wearing a white shirt when talking RNNs
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'
@ 20:00 isn't h sub t acting as the bias for each step in the rnn?
so what would be the the past memory at time stamp 0, (Xo , h-1) ?
Bode Divide
Is this topic harder, or does Alexander teach better?
not as clear as alexander's explanation of the technical details in the first lecture unfortunately, big picture slides are good though
17:51
thanks daddy
Miss was stressed if she made the presentation complex
Caesar Harbor
Testing
CatGPT? :D 58m:51s
❤❤
Alex is so much better at presenting.
Because he is a man.
Totally disagree. They’re both excellent. This is a difficult topic to break down.
✋🏻
she doesn't have a firm grasp of the topic
wonderful
Hello from PRC
When lab code will be released?
ATTENTION | NOITNETTA
Truly amazing lecture! Thank you