11 ай бұрын
Жыл бұрын
Жыл бұрын
Жыл бұрын
2 жыл бұрын
2 жыл бұрын
3 жыл бұрын
3 жыл бұрын
3 жыл бұрын
3 жыл бұрын
4 жыл бұрын
4 жыл бұрын
Пікірлер
@xiongyujasperchen3154 15 сағат бұрын
So well explained that makes it easy to understand GAN. Thank you. Big thumb up.
@just_a_viewer5 19 сағат бұрын
amazingly taught. thank you so much!
@nettrogenium. 21 сағат бұрын
thanks dude, couldn't understand any explanation of all that before i found your video
@aapje180 Күн бұрын
Bedankt
@SerranoAcademy 15 сағат бұрын
Thank you so much for your kind contribution @aapje180! It's very much appreciated. :)
@tiagomelojuca7851 Күн бұрын
+1 sub, great explanation, amazing how u make the math theory fits so well in the subject
@harsharangapatil2423 Күн бұрын
Can you please add a video on curse of dimensionality?
@SerranoAcademy 15 сағат бұрын
Great idea, thank you!
@tanggenius3371 2 күн бұрын
Thanks, the explaination is so intuitive. Finally understood the idea of attention.
@unclecode 2 күн бұрын
Appreciate the great explanation. I have a question regarding the clipping formula at 36:42. You have used the "min" function. For example, if the rate is 0.4 and the epsilon is 0.3, indicating that we should get 0.7 in this scenario. However, in the formula you introduced here is returns then 0.4. Shouldn't the formula be clipped_f(x) = max(1 - epsilon, min(f(x), 1 + epsilon))? Am I missing anything?
@WrongDescription 3 күн бұрын
Best explanation on the internet!!
@camzbeats6993 3 күн бұрын
Top
@camzbeats6993 4 күн бұрын
Very intuitive, thanks you. I like the exemple approach you take. 👏
@saralagrawal7449 4 күн бұрын
Ye Be10x ko koi ban kardo please. Irritate kar diya hai.
@Cathiina 4 күн бұрын
Yess true. I only passed all my maths courses by learning by heart. Never quite satisfied with even good grades because I knew in my heart I understood nothing. Currently refreshing linear algebra in your coursera course and WOW! It’s addicting to actually learn what a rank in a matrix means. 😊☀️
@HoussamBIADI 4 күн бұрын
Thank you for this amazing explanation <3
@mekuzeeyo 5 күн бұрын
Great video as always. I have a question, in practice which one works best using DPO or RLHF?
@SerranoAcademy 4 күн бұрын
Thank you! From what I've heard, DPO works better, as it trains the network directly instead of using RL and two networks.
@mekuzeeyo 4 күн бұрын
@@SerranoAcademy Thank you sir for the great work. your Coursera courses have been awesome.
@hyperbitcoinizationpod 5 күн бұрын
And the entropy is number of bits needed to convey the information.
@martadomingues1691 5 күн бұрын
Very good video, it helped clear some doubts I was having with this along with the Viterbi Algorithm. It's just too bad that the notation used was too different from class, but it did help me understand everything and make a connection between all of it. Thank you!
@Cathiina 6 күн бұрын
Hi Mr. Serrano! I am doing your coursera course at the moment on linear algebra for machine learning and I am having so much fun! You are a brilliant teacher, and I just wanted to say thank you! Wish more teachers would bring theoretical mathematics down to a more practical level. Obviously loving the very expensive fruit examples :)
@SerranoAcademy 6 күн бұрын
Thank you so much @Cathiina, what an honor to be part of your learning journey, and I’m glad you like the expensive fruit examples! :)
@vigneshram5193 6 күн бұрын
Thank you Luis Serrano for this super explanatory video
@bin4ry_d3struct0r 7 күн бұрын
Is there an industry standard for the KLD above which two distributions are considered significantly different (like how 0.05 is the standard for the p-value)?
@SerranoAcademy 7 күн бұрын
Ohhh that’s a good question. I don’t think so, since normally you use it for minimization or comparison between them, but I’ll keep an eye, maybe it would make sense to have a standard for it.
@frankl1 7 күн бұрын
Did anyone expect something different than Sofmax regarding the Bradley-Terry model as myself? 😅
@SerranoAcademy 7 күн бұрын
lol, I was expecting something different too initially 🤣
@frankl1 7 күн бұрын
Really love the way you broke down the DPO loss, this direct way is more welcome by my brain :). Just one question on the video, I am wondering how important it is to choose the initial transformer carefully. I suspect that if it is very bad at the task, then we will have to change the initial response a lot, but because the loss function prevents from changing too much in one iteration, we will need to perform a lot tiny changes toward the good answer, making the training extremely long. Am I right ?
@SerranoAcademy 7 күн бұрын
Thank you, great question! This method is used for fine-tuning, not specifically for training. In other words, it's crucial that we start with a fully trained model. For training, you'd use normal backpropagation on the transformer, and lots of data. Once the LLM is trained and very trusted, then you use DPO (or RLHF) to fine-tune it (meaning, post train it to get from good to great). So we should assume that the model is as trained as it can, and that's why we trust the LLM and we try to only change it marginally. If we were to do this method to train a model that's not fully trained... I'm not 100% if it would work. It may or may not, but we'd still have to punish the KL divergence much less. And also, human feedback gives a lot less data than scraping the whole internet, so I would still not use this as a training method, more as refining. Let me know if you have more questions!
@frankl1 7 күн бұрын
@@SerranoAcademy Thanks for the answer, I understand better. I forgot that this design is for fine-tuning.
@rb4754 7 күн бұрын
Very nice lecture on attention.
@mayyutyagi 7 күн бұрын
Now whenever I watch Serrano's video, I first like it and the start watching it coz I know the video will gonna be outstanding as always.
@mayyutyagi 7 күн бұрын
Liked this video and subscribed your channel today.
@mayyutyagi 7 күн бұрын
Amazing video... Thanks sir for this pictorial representation and explaining this complex topic with such an easy way.
@AravindUkrd 8 күн бұрын
Thanks for the simplified explanation. Awesome as always. The book link in the description is not working.
@SerranoAcademy 7 күн бұрын
Thank you so much! And thanks for letting me know, I’ll fix it
@johnzhu5735 8 күн бұрын
This was very helpful
@siddharthabhakta3261 8 күн бұрын
The best explanation & depiction of SVD.
@melihozcan8676 8 күн бұрын
Thanks for the excellent explanation! I used to know the KL Divergence, but now I understand it!
@saedsaify9944 8 күн бұрын
Great one, the simpler it looks and harder to build!
@stephenlashley6313 8 күн бұрын
This and your whole series of attention NN is a thing of beauty! There are many ways of simplifying this here, but you come the closest to understanding Attention NN and QC are identical and QC is much better. In my opinion QC has never been done correctly, the gates are too confusing and poorly understood. QC is not still in simplified infant stage, it is mature what QC can do and matches all Psychology observations. All problems in Biology and NLP are sequences of strings.
@cloudshoring 8 күн бұрын
awesome!
@bifidoc 9 күн бұрын
Thanks!
@SerranoAcademy 9 күн бұрын
Thank you so much for your kind contribution @bifidoc!!! 💜🙏🏼
@user-xc8vy4cw9k 9 күн бұрын
I would like to say thank you for the wonderful video. I want to learn reinforcement learning for my future study in the field of robotics. I have seen that you only have 4 videos about RL. I am hungry for more of your videos. I found that your videos are easier to understand because you explain well. Please add more RL videos. Thank you 🙏
@SerranoAcademy 9 күн бұрын
Thank you for the suggestion! Definitely! Any ideas on what topics in RL to cover?
@user-xc8vy4cw9k 7 күн бұрын
@@SerranoAcademy more videos in the field of Robotics please. Thank you. You may also guide me how I can approach the study of reinforcement learning.
@user-xc8vy4cw9k 9 күн бұрын
I would like to say thank you for the wonderful video. I want to learn reinforcement learning for my future study in the field of robotics. I have seen that you only have 4 videos about RL. I am hungry for more of your videos. I found that your videos are easier to understand because you explain well. Please add more RL videos. Thank you 🙏
@Omsip123 9 күн бұрын
So well explained
@guzh 9 күн бұрын
DPO main equation should be PPO main equation.
@epepchuy 10 күн бұрын
Exvelente explciacion!!!
@iantanwx 10 күн бұрын
Most intuitive explanation for QKV, as someone with only an elementary understanding of linear algebra.
@VerdonTrigance 10 күн бұрын
It's kinda hard to remember all of these formulas and it's demotivating me from further learning.
@javiergimenezmoya86 10 күн бұрын
You do not have to remember that formulas. You only have to understand the logic in them.
@SerranoAcademy 15 сағат бұрын
Thanks for your comment @VerdonTrigance! I also can't remember these formulas, since to me, they are the worst way to convey information. That's why I like to see it with examples. If you understand the example and the idea underneath, then you understand the concept. Don't worry about the formulas.
@SerranoAcademy 15 сағат бұрын
Agreed @javiergimenezmoya86!
@IceMetalPunk 10 күн бұрын
I'm a little confused about one thing: the reward function, even in the Bradley-Terry model, is based on the human-given scores for individual context-prediction pairs, right? And πθ is the probability from the current iteration of the network, and πRef is the probability from the original, untuned network? So then after that "mathematical manipulation", how does the human-given set of scores become represented by the network's predictions all of a sudden?
@user-xc8vy4cw9k 10 күн бұрын
Thank you for the wonderful video. Please add more practical example videos for the application of reinforcement learning.
@SerranoAcademy 10 күн бұрын
Thank you! Definitely! Here's a playlist of applications of RL to training large language models. kzfaq.info/sun/PLs8w1Cdi-zvYviYYw_V3qe6SINReGF5M-
@laodrofotic7713 10 күн бұрын
noone of the videos I seen on this subject actually explain where the hell qkv values come from! its amazing people jump on making video while not understanding the concepts clearly! I guess youtube must pay a lot of money! But this video does a good job of explaining most of the things, it never does tell us where the actual qkv values come from, how do the embendings turn into them, and actually got things wrong in my oppinion. the q comes from embeddings that are multiplied by the wq, which is a weight and parameter in the model, but then the question is, where does wq wk wv come from???
@bendim94 10 күн бұрын
how do you choose the number of features in the 2 matrices, i.e. how did you choose to have 2 features only?
@Priyanshuc2425 10 күн бұрын
Hey I know this 👦. He is my Maths teacher who don't only teach but make us visualize why we learn the topic and how will it useful in real world ❤
@Q793148210 10 күн бұрын
It‘s was just so clear. 😃
@DienTran-zh6kj 10 күн бұрын
I love his teaching, he makes complex things seem simple.
@shouvikdey7078 10 күн бұрын
Love your videos, please make more such videos on mathematical description of generative models such as GAN, Diffusion, etc.
@SerranoAcademy 10 күн бұрын
Thank you! I got some on GANs and Diffusion models, check them out! GANs: kzfaq.info/get/bejne/brJhZMR-s5uviWw.html Stable diffusion: kzfaq.info/get/bejne/gNNxh9d4ld-lZXk.html
@mohammadarafah7757 11 күн бұрын
We expect to describe wasserstein distance 😊
@SerranoAcademy 10 күн бұрын
Ah good idea! I'll add it to the list, as well as earth-mover's distance. :)
@mohammadarafah7757 10 күн бұрын
@SerranoAcademy I also highly recommend to describe Explainable AI (XAI) which depends on statistics.