Building makemore Part 2: MLP

[@farhadkarimi]

It’s insanely awesome that you are taking time out of your day to provide the public with educational videos like these.

[@OlleMattsson]

0% hype. 100% substance. GOLD!

[@WouterHalswijk]

I'm a senior aerospace engineer, so no CS or ML training at all, and I'm now totally fascinated with PyTorch. First that micrograd intro, which totally clicked the methods used for backprop into place. Now this intro with embedding and data preparation etc. I almost feel like transformers are within reach already. Inspiring!

[@rajaahdhananjey4803]

Quality Engineer with a Production Engineering background. Same feeling !

[@staggeredextreme8213]

How you guys landed here, i mean me as a cs graduate, I'll never land directly to a lecture series of aerospace that suddenly start to make sense 🤔

[@shashankmadan]

@@staggeredextreme8213 aerospace engineer's are far more intelligent than CS engs for sure.

[@staggeredextreme8213]

@@shashankmadan i wish you were correct but unfortunately you are wrong

[@maercaestro]

@@staggeredextreme8213 engineers apart from computer engineer rarely feels the need to share knowledge freely. closeted

[@rmajdodin]

53:20 To break the data to training, developement and test, one can also use torch.tensor_split. n1 = int(0.8 * X.shape[0]) n2 = int(0.9 * X.shape[0]) Xtr, Xdev, Xts = X.tensor_split((n1, n2), dim=0) Ytr, Ydev, Yts = Y.tensor_split((n1, n2), dim=0)

[@peterwangsc]

This is amazing. Using just a little bit of what I was able to learn from part 3, namely the Kaiming init, and turning back on the learning rate decay, I was able to achieve 2.03 and 2.04 in my test and validation with a 1.89 in my training loss with just 300k iterations and 23k parameters. I set my block size to 4 and my embeddings to 12 and increased my hidden layer to 300 while decaying my learning rate exponent from -1 to -3 linear space over the 300k steps. All that without even using batch normalization yet. After applying batch norm, was able to get these down to 1.99 and 1.98 with training loss in the 1.7s after a little more tweaking. Really good content in this lecture, it really has me feeling like a chef in the kitchen almost, cooking up a model with a few turns of the knobs...This sounds like a game or a problem that can be solved with an AI trained on turning knobs.

[@peterwangsc]

intuition: why 4 block size instead of 3 block size? well the english language i think has an average of somewhere between 3 to 5 characters per syllable, which most 1 syllable names falling between that 3-5 character bucket and some 2 syllable names falling in that 4-6 character bucket and beyond. I wanted a block size that would give some better indication on whether we're in a one syllable or two syllable context, and so we could end up with some more pronounceable names. It also just made sense to scale up the dimension of embeddings and neurons to give a little more nuance to the relationships between the different context blocks. English has so many different rules when it comes to vowels and silent letters and so I felt like we needed to give enough room for 3-4 degrees of freedom for each character in the context block, and therefore needed more neurons in the net to account for those extra dimensions. running the model for more steps just allows the convergence to happen. I don't know if it could get much better after more steps but this took 6-7 minutes to run so I think i squeezed all that I could out of these hyperparams.

[@JeavanCooper]

Deeply sympathetic! I always feel like deep learning is a lot like cooking or building blocks.

[@INGLERAJKAMALRAJENDRA]

Thanks for sharing your experience :)

[@rmajdodin]

A two hour workshop on NLP with transformers costs 149$ in Invidia GTC conference. You tutor us with amazing quality for free. Thank you!🙂

[@rayallinkh]

Pls continue this series(and similar ones) to eternity! You are THE teacher which everyone interested/working in AI really needs!

[@jerinjohnkachirackal]

[phone])

[@anveshicharuvaka2823]

Hi Andrej, Even though I am already familiar with all this I still watch your videos for the pedagogical value and for learning how to do things. But, I still learn many new things about pytorch as well as how to think through things. The way you simplify complex stuff is just amazing. Keep doing this. You said on a podcast that you spend 10 hours for 1 hour of content, but you save 1000s of hours of frustration and make implementing ideas a little bit easier.

[@Sovereign589]

great and true sentence: "You said on a podcast that you spend 10 hours for 1 hour of content, but you save 1000s of hours of frustration and make implementing ideas a little bit easier."

[@ncheymbamalu4906]

Much thanks, Andrej! I increased the embedding dimension to 5 from 2, initialized the model parameters from a uniform distribution [0, 1) instead of a standard normal distribution, increased the batch size to 128, and used the sigmoid activation for the hidden layer instead of the hyperbolic tangent, and was able to get the negative log-likelihood for the train and validation sets down to ~2.15, respectively.

[@matjazmuc-7124]

I just want to say thank you Andrej, you are the best ! I've spent the last 2 days going over the first 3 videos (and completing the exercises), I must say that this is by far the best learning experience I ever had. The quality of the lectures is just immeasurable, in fact you completely ruined how I feel about lectures at my University.

[@ahmedivy]

where are the exercises?

[@sam.rodriguez]

Check the comments from Andrej in each video @@ahmedivy

[@allahm-ast3mnlywlatstbdlny164]

​@@ahmedivydescription

[@shaypeleg7812]

@@ahmedivyAlso asked myself, then found them in the movie description: Exercises: - E01: Tune the hyperparameters of the training to beat my best validation loss of 2.2 - E02: I was not careful with the intialization of the network in this video. (1) What is the loss you'd get if the predicted probabilities at initialization were perfectly uniform? What loss do we achieve? (2) Can you tune the initialization to get a starting loss that is much more similar to (1)? - E03: Read the Bengio et al 2003 paper (link above), implement and try any idea from the paper. Did it work?

[@caeras1864]

Thanks. Seeing things coded from scratch clears up any ambiguities one may have when reading the same material in a book.

[@moalimus]

Can't believe the value of these lecture and how helpful they are, you are literally changing the world. Thanks very much for your effort and knowledge

[@manuthegameking]

This is amazing!!! I am an undergraduate student researching deep learning. This series is a gold mine. The attention to detail as well as the intuitive explanations are amazing!!

[@pulkitgarg189]

Reminder - please create a video on internal of torch tensor and how it works. Thanks!!

[@cangozpinar]

Thank you very much for taking your time to go step by step whether it be torch API, your code or the math behind things. I really appreciate it.

[@koenBotermans]

I believe that at 49:22 the losses and the learning rates are misaligned. The first loss (derived from completely random weights) is computed before the first learning rate is used, and therefor the first learning rate should be aligned with the second loss. You can simply solve this problem by using this snippet; lri = lri[:-1] lossi = lossi[1:] Also, thank you so much for these amazing lectures

[@mdmusaddique_cse7458]

I was able to achieve a loss of 2.14 on test set Some hyperparameters: Neurons in hidden layer: 300 Batch size: 64 for first 400k iterations then 32 for rest Total Iterations: 600,000 Thank you for uploading such insightful explanations. I really appreciate that you explained how things work under the hood and insights of PyTorch's internals.

[@louiswang538]

29:20 we can also use torch.reshape() to get the right shape for W. However, there is a difference between torch.view and torch.reshape TL;DR: If you just want to reshape tensors, use torch.reshape. If you're also concerned about memory usage and want to ensure that the two tensors share the same data, use torch.view.

[@myanxiouslife]

So cool to see the model learn through the embedding matrix that vowels share some similarity, 'q' and '.' are outlier characters, and so on!

[@mbpiku]

Never understood the basics of hyper parameter tuning so well. A sincere Thanks for the foundation and including that part in this video.

[@pulkitgarg189]

Also will be really helpful if you can turn your keyboard input visible as on. Would be really helpful to see what all shortcuts can be used. Thanks!

[@vulkanosaure]

Thank you so much, this is gold, I'm watching all of this thoroughly, pausing the video a lot to wrap my head around those tensors manipulation (i didn't know anything abt python/numpy/pytorch). I'm also really inspired from how you quickly plot datas to get important insights, I'll do that too from now on

[@cristobalalcazar5622]

This lecture compress an insanely amount of wisdom in 1.15hrs! Thanks

[@vil9386]

Can't thank you enough. It's such a satisfying feeling to understand the logic under the ML models clearly. Thank you!

[@SandeepAitha]

Watching your videos constantly reminds me of "There are no bad students but only bad teachers"

[@rezathr8968]

Really enjoyed watching these lectures so far :) also +1 for the PyTorch internals video (@25:36)

[@pedroaugustoribeirogomes7999]

Please create the "entire video about the internals of pytorch" that you mentioned in 25:40. And thank you so much for the content, Andrej !!

[@joshwolff4592]

The amount of times in college we used the PyTorch "view" function with ZERO explanation. And your explanation is not only flawless, you even make the explanation itself look easy! Thank you so much

[@grayboywilliams]

So many insights, I’ll have to rewatch it again to retain them all. Thank you!

[@jackjayden1162]

This whole Neural Networks: Zero to Hero series is just phenominal, absolutely some of the best content out there in the internet, top notch knowledges well taught by industry leading figure yet in such a patient and practical manner! We couldn't thank you enough for the remarkable work you did for the community!

[@tylerxiety]

Love all the tips and explanations on pytorch, training efficiency, and educational purposed errors. I was writing both code and notes and rewatching and enjoyed it and felt having a fruitful day after finished. It's like I was learning with a kind and insightful mentor sitting next to me. Thanks so much Andrej.

[@mehulsuthar7554]

I am deeply grateful to all the effort and time you have put in this. Thank you so much. i tried to do various kind of weights initialization and got the accuracy of 2.03 on test and 2.08 on dev. I am still going on but i wanted to appreciate the work you have done. Once again thank you. wishing you a better health and life.

[@SK-ke8nu]

Great work Andrej! It is a rare skill to be able to explain such complex topics to people without your background. Hats off!!

[@ShouryanNikam]

What a time to be alive, someone as smart as Andrej giving away for free probably the best lectures on the subject. Thanks so much!!!

[@bassRDS]

Thank you Andrej! I find your videos not only educational, but also very entertaining. Learning new things is exciting!

[@PrarthanaShah-nk1xh]

We need more of this!!!!! The way he explains part by part, with maths, unreal

[@myao8930]

@00:45:40 'Finding a good initial learning rate', each learning rate is used just one time. The adjustment of the parameter of one learning rate is based on the parameters already adjusted using the prior smaller learning rates. I feel that each of the 1,000 learning rate candidates should go through the same number of iterations. Then, the losses at the end of the iterations are compared. Please tell me if I am wrong. Thanks!

[@wolk1612]

each time you make exponentially bigger steps, so you can neglect previous path. It's like if you make one step toward your goal, and than make another 10 steps your overall path is not really affected by you first step. And generally you want to find the biggest number of steps (lr) which you should take in some direction (gradient) to not overshoot your goal (best model weights) to get there faster.

[@myao8930]

Thanks! The instructor says the test should not be run many times since each time the model learns something from the test data. In the test, the parameters are not adjusted. How can the model learn from the test data?@@wolk1612

[@DrKnowitallKnows]

Thank you for referencing and exploring the Bengio paper. It's great to get academic context on how models like this were developed, and very few people actually do this in contexts like this.

[@JayPinho]

Great video! One question, @AndrejKarpathy: around 50:30 or so you show how to graph an optimal learning rate and ultimately you determine that the 0.1 you started with was pretty good. However, unless I'm misunderstanding your code, aren't you iterating over the 1000 different loss function candidates while *simultaneously* doing 1000 consecutive passes over the neural net? Meaning, the loss will naturally be lower during later iterations since you've already done a bunch of backward passes, so the biggest loss improvements would always be stacked towards the beginning of the 1000 iterations, right? Won't that bias your optimal learning rate calculation towards the first few candidates?

[@bres6486]

I found this a little confusing too since the expectation is to do 1000 steps of gradient descent with each learning rate separately. I think this trick of simultaneously changing learning rate while training (on mini-batches) is just a quick way to broadly illustrate how learning rate changes impact the loss. If the learning rate is too low initially then the loss will decrease very slowly, which is what happens. When the learning rate increases the loss decrease is more rapid. When the learning rate is too high the loss becomes unstable (can increase).

[@yiannigeorgantas1551]

Whoa, you’re putting these out quicker than I can go through them. Thank you!

[@bebebewin]

This is perhaps the best series on KZbin I have ever seen - Without a doubt I can't recall the last time a 1 hour video was able to teach me so much!

[@zmm978]

I watched and followed many such courses, yours are really special, easy to understand yet very indepth, with many useful tricks.

[@Joseph_Myers]

I wanted to let you know i listened to the podcast with Lex Fridman and i know understand how much of a Rockstar you are in the Artificial Intelligence space. Like many others i appreciate you and all you qre doing to push forward with this incredible technology. Thank you.

[@alelmcity]

Hi Andrej, Really amazing work, big thank you! However, I am a bit confused about specifying a good initial learning rate. because in the presented approach the recoded loss of a learning rate is affected by the previous optimization iterations. Shouldn't we for each learning rate optimize for a certain number of iterations, save the average loss and then reinitialize the params and off to the next learning rate? Finally, select the best-performing learning rate.

[@styssine]

I'm confused too. Shouldn't there be a double loop, with outer loop scanning the learning rates, and the inner loop doing a relatively small number of iterations?

[@julian1000]

This is absolutely amazing stuff, thank you so much for putting this out for FREE!!!! I thought your name looked familiar and then I remembered you sparked my initial interest in NNs with "the unreasonable effectiveness of RNNs". It was SO fun and fascinating to just toss any old random text at it and see what it did! Can't believe how much progress has happened so quickly. Really really excited to get a better practical understanding of NNs and how to program them. Thank you again!

[@alexandermedina4950]

This is priceless, you have such a low and high level understanding of the topic, that's just amazing.

[@timilehinfasipe485]

Thank you so much for this, Andrej !! I’m really learning and enjoying this

[@not_elm0]

This educational vid will reach more students than a regular teaching job at a regular school. Thanks for sharing & giving back👍

[@RickeyBowers]

Such a valuable resource to help people in other fields get up to speed on these concepts. Thank you.

[@ncheymbamalu4013]

Andrej, I was able to get a train and validation cross-entropy of 2.0243 and 2.1333, respectively. The hyperparameters that were changed were...the number of characters used to predict the next character (from 3 to 5), the length of each embedding vector (from 2 to 27, i.e., the number of tokens), and the batch size (from 32 to 128). Also, after optimizing the learning rate, I took the average of the 10 learning rates that produced the lowest cross-entropy and trained the model with it. Finally, I decreased that 'averaged' learning rate even further by an order of two magnitudes and trained the model one last time. In short, a lot of experimentation was required. Haha.

[@varunjain8981]

Beautiful......The explanation!!!! This builds the intuition to venture out in unknown territories. Thanks from the bottom of my heart.

[@shreyasdaniel627]

You are amazing! Thank you so much for all your work :) You explain everything very intuitively!!! I was able to achieve a train loss of 2.15 and test loss of 2.17 with block_size = 4, 100k iterations and embed dimension = 5.

[@anangelsdiaries]

I am so happy people like you exist. Thank you very much for this video series.

[@shaypeleg7812]

hi Andrej, Your lectures are the best ones I saw. It's amazing you take complex ideas and explain them in such a level that even beginners understand. Thank you for that.

[@ggir9979]

I got the loss on the training set under 2 (1.9953 to be exact). But this was a clear case of overfitting as the regularisation loss actually increased to 2.1762 🙂 HyperParameters: wordDim ( C ) = 15 layerDim (W1 output/W2 input)= 500 iterations = 400000 batchSize = 100

[@kordou]

Andrey thank you for this great series of lectures. you are a great Educator! 100% GOLD Material to Learn

[@gilad13886]

Amazing video and series ! thank you. Small correction to the build_makemore_mlp.ipynb colab it's assuming the embedding size is 2 but eventually during the lecture it was changed to 10 so the emb.shape will be (32, 3, 10) and h.shape (32, 200), just FYI if you're running it and get confused

[@AlexLukeKoval]

Hi @AndrejKarpathy 17,000 words in 30 dimensions is not cramped at all. 2^30 ≈ 1 billion. This means that 30 dimensions can support 1 billion points with each point being on the opposite side of axis to every other point. Consider the 3D case: with 8 points forming a cube around the origin (1,1,1) (1,1,-1)...(-1,-1,-1) For each point, every other point is on the opposite side of at least one axis, they are at least distance 2 apart. Each point has it's own 'corner' of the space - it's the same in 30 dimensions.

[@nginfrared]

Your lectures make me feel like I am in an AI Retreat :). I come out so happy and enriched after each lecture.

[@lashgar]

If you wonder what does the second dimension of matrix 27xN C represent/learns, it is a set of "word features". Every word (actually a token in Andrew's example) is represented in N dimensional space and the model learns N different features of the word. The feature vector can be used for classification of the word and yield higher probability for the word in the sentences training didn't see by leveraging weights trained by its neighbors in the cluster. The paper is great source to learn more, as Andrej emphasized.

[@oxente_aquarios]

The world needs to know about this youtube series. I already published it to my network on linkedin.

[@TheEbbemonster]

I really enjoy these videos! A little note is that to run through the tutorial, it requires a bit of memory, so it would be nice with an early discussion of batching :) I run out of memory when calculating the loss, so had to reduce the sample size significantly.

[@nullne]

there is one tiny bug around stepi, which will reset to 0, 1, 2 ... in each iteration, so that the plot will overlap

[@pastrop2003]

On top of everything else, this is absolutely the best documentation & explainer of PyTorch. This is infinitely better that the PyTorch documentation. In fact, it should be a must-see video for the PyTorch team to show them how to write good documentation. Meta should pay Adrej any fee he asks for the rights to use this video in the PyTorch docs...Thank you Andrej!

[@softwaredevelopmentwiththo9648]

It's one of the great pleasures of KZbin to be taught by someone with Andrejs experience. Your series is honestly one of the best on KZbin. It's not too short like the typical DL intro videos. And it's not boring because you build the solution from the ground up with real code and common errors included. I love the format and the clear and concise structure. Thank you for the work that you put into these videos.

[@jeffreyzhang1413]

One of the best lectures on the fundamentals of ML

[@8eck]

I like how Andrej is operating with tensors, that's super cool. I think that we need a separate video about that from Andrej. It is super important.

[@Yenrabbit]

Really great series of lessons! Lots of gems in here for any knowledge level. PS: Increasing the batch size and lowering the LR a little does result in a small improvement in the loss. Throwing out 2.135 as my test score to beat :)

[@Democracy_Manifest]

What an amazing teacher you are. Thank you

[@american-professor]

I cannot believe word2vec was invented in 2003 instead of 2014

[@arildboes]

As a programmer trying to learn ML, this is gold!

[@alexandertaylor4190]

I feel pretty lucky that my intro to neural networks is these videos. I've wanted to dive in for a while and I'm hooked already. Absolutely loving this lecture series, thank you, I can't wait for more! I'd love to join the discord but the invite link seems to be broken

[@alexanderliapatis9969]

I am into neural nets the last 2 years and i think i know some stuff about them (the basics at least) and i have taken a couple of courses and stuff about ml/dl. I was always wandring why do i need val and test set, why test the model on 2 different sets of the same data. So hearing that the val set is for finetuning of hyperparameters is a first for me and the fact that you use test set a few times in order to avoid overfitting on it as well. I am amazed by the content on your videos and the way you teach things. Keep up the good work, you are making the community a better place.

[@tarakivu8861]

I dont understand the overuse of the test-set. I mean we are only forward-passing that to evaluate the performance, so we arent learning anything? I can maybe see it when the dev sees the result and changes the network to better fit the test-case? But thats good isnt it?

[@debdeepsanyal9030]

@@tarakivu8861 For the people later who will maybe stumble upon this comment and probably has the same doubt, here's an intuition i have that gives me a pretty thorough understanding. Say you are studying for an exam, and you use your textbooks for learning (note the use of learning here as well). Now, you want to know how good you're doing with the content you're learning from the textbooks, hence you give a mock exam, which kind of replicates the feeling of the final exam you're going to give. So you give test on the mock paper, and you note the mistakes or errors you are making on the mock paper, and you keep studying the text books and you give the mock test over and over again, periodically. After some time, you kind of have an estimate of how well you are going to do in the final exam based off the results you are getting on the mock exam. Here, learning from the textbooks is the model training on the train set. The mock exam, is the validation set. The final exam (which you just give once), is like the test set. Note that Dev set doesn't really change the network in any form or matter, it just gives us an estimate of how the model can perform on the test set. It's like if you are performing bad on the mock test, you know you can't make stuff better for the final exam.

[@jamesmichaelmcdermot]

The dataset consists of the set of unique names, which tends to over-emphasise weird names and eccentric spellings. The generated names are representative of the dataset but less representative of real names. To avoid the problem we could weight the dataset by frequency of name usage in the real world.

[@_jeeves_]

An alternative to emb.view(-1, 6) is emb.flatten(start_dim=1) which also returns a view in this case and has the advantage of not having to specify the length of the concatenated embeddings. Also, I don't know if there's really any advantage, but an alternative to prob[torch.arange(32), Y] would be prob.index_select(dim=1, index=Y)

[@DanteNoguez]

I love the simplicity of your explanations. Thanks a lot!

[@ShadoWADC]

Thank you for doing this. This is truly a gift for all the learners and enthusiasts of this field!

[@AbhishekVaid]

37:14, who would tell you this when you are reading from a book. Exceptional teaching ability

[@ilyas8523]

underrated series. Very informative. Watching this series before jumping into the Chatbot video. I am currently building my own poem-gpt

[@LambrosPetrou]

Awesome videos, thank you for that! I have a question though about 45:00, "finding a good initial learning rate", which is either a mistake in the video or I misunderstood something. In the video, you iterate over the possible learning rates, while we do a single training iteration. This means that the learning rates towards the end are going to have a smaller loss (usually), than the first learning rates. This seems to be biasing towards choosing learning rates from the end. Shouldn't we have another outer loop that iterates the learning rates, and then an inner loop that does our actual training PER learning rate, and then keep track of the final loss per learning rate? Thanks!

[@pranjaldasghosh2588]

i believe this may not prove necessary as he re-initialises the weights for every learning rate, thus starting with a fresh slate

[@oshaya]

Amazing, astounding… Andrej, you’re continuing your revolution for people’s education in ML. You are the “Che” of AI.

[@isaacfranklin2712]

Quite an ominous comparison, especially with Andrej working at OpenAI now.

[@jeevan288]

what does "Che" mean?

[@gregoriovilardo]

​@@jeevan288 is a murderer that fight "for" cuba. "Che Guevara"

[@GraTen]

Great video! I improved the initialization and tweaked the hyperparameters. Finally, got 2.02 on the test set!🥳

[@MihaiNicaMath]

I was so disappointed at the end because we never got to see any fun samples, so I was thrilled by the extra notes at the end showing this! (I also have determined the names of my next two pets will be "Mor" and "Ham")

[@AndrejKarpathy]

:D :D :D

[@yukselkapan9996]

Both of these are valid Turkish words! "Mor" means purple and "Ham" means raw/crude 🙂

[@MrNonDivine]

Mother and him in danish :)

[@yogendramiraje8962]

If someone sorts all the NN courses, videos, MOOCs by their density of knowledge in descending order, this video will be at the top.

[@mohamedlamnaouar2175]

This is amazing, Thank you for sharing this content, I forget when you have said you don't do this on industry "production", can you make a video which you can talk a little bit about how to improve production in industry using pytorch, also common mistakes in industry !!! if you don't have a problem. again thank you so much for this useful content

[@ayogheswaran9270]

Thank you, Andrej!! Thanks a lot for all the efforts you have put in❤

[@aangeli702]

Andrej is the type of person that could make a video titled "Building a 'hello world' program in Python" which a 10x engineer could watch and learn something from it. The quality of these videos is unreal, please do make a video on the internals of torch!

[@Tldrx]

How can I become genius like you? And your are so generous to share your knowledge... Surely god gave you to us, to make the world better.

[@svassilev]

Great stuff @AndrejKarpathy! I actually was typing in parallel in my own notebook, as I was training on a different dataset. Amazing!

[@fertwvnbxcbwrtrecvbvcx]

To the other viewers: Do you have recommendations to channels of similar quality? This is a goldmine

[@wolpumba4099]

kzbin.info

[@eitanporat9892]

I don't think you will find something similar to this in quality :)

[@soggy8761]

Jeremy Howard

[@xDMrGarrison]

I finally beat 2.17, with 2.14. With context_size:4, embedding_dimension:5, hidden_dimension:300, total_iterations:200000, batch_size:800. And now for practice I am going to make a neural network to predict another kind of sequence. (I'm in the process of preparing/shaping the data, which is not easy) Fun stuff :P Really fiending for that next video though xD I'm excited to learn about RNNs and Convnets and especially transformers.

[@hamza1543]

Your batch size should be a power of 2

[@JohnDoe-ph6vb]

at 21:24 I think it's supposed to be first letter not first word. It's first word in the paper but first letter in the example

[@jkscout]

correct, but if you also inspect the vectors... this does not make sense... there are 32 of them, and remember these were the running characters for the first 5 words... so this has to be representative of more than the first character

[@vincentyovian5480]

I've never been this excited for a lecture video before

[@КонстантинДемьянов-л2п]

not sure why you keep mentioning that ideal model would have probabilities of 1 assigned to the next character. this would only be true in situation when in training data there isn't a single case of the same two characters followed by two different characters.

[@Oler-yx7xj]

I assume he means an ideal model with an ideal architecture, not just one of this specific architecture ideally trained.

[@LusidDreaming]

He explains later why you cannot achieve an ideal model because of this very reason. He's using the term "ideal model" to refer to a model with a loss of 0, which he then later explains is impossible because the dataset is not one-to-one. In general, an "ideal" classification model will output a probability of 1 for the correct class, which is the only way to achieve zero loss against a one-hot encoding. This is more of a theoretical idea than an actual goal in most cases.

[@minhajulhoque2113]

Such an amazing educational video. Learned a lot. Thanks for taking the time and explaining many concepts so clearly.

[@arunmanoharan6329]

Thank you so much Andrej! This the best NN series. Hope you will create more videos:)

[@SagiPolaczek]

man this series should be on netflix

[@avishakeadhikary]

It is an absolute honor to learn from the very best. Thanks Andrej.

[@kl_moon]

I feel so excited that the question i had last video about why the loss cant be zero had interpolated in this video lol. SO EXCITED!!!!!!

[@atgctg]

This is great, thanks Andrej! Also, I wanted to share a small suggestion: On smaller screens it might be hard to see the code, so it would be great if the jupyter window was in full screen or zoomed in a bit:)

[@AndrejKarpathy]

I already zoomed it in from my first video, can try one more notch ty