"Not in this data set" is my new favorite comeback oneliner

@MrAmgadHasan

Жыл бұрын

It's similar to "not in this timeline" that we hear a lot in time-travel scifi

@Jason-wm5qe

Жыл бұрын

😂

“What does the fox say?” “Don’t they go ‘ring ding ding’?” “Not in this dataset”

4 жыл бұрын

Train the same algorithm on songs instead of news articles and I figure you could get some really interesting results as well. Songs work on feelings and that should change the connections between the words as well - I bet the technology can be used to tell a lot about the perspective people take on things as well.

@argenteus8314

4 жыл бұрын

@ Songs also use specific rhythmic structures; assuming most of your data was popular music, I bet that there'd be a strong bias for word sequences that can fit nicely into a 4/4 time signature, and maybe even some consistent rhyming structures.

@killedbyLife

4 жыл бұрын

@ Train it with only lyrics from Manowar!

@ruben307

4 жыл бұрын

@ I wonder how strong Rhymes would show up in that dataset.

4 жыл бұрын

@@killedbyLife That's odd - I listen to Manowar regularly. Nice pick. 😉

Tomorrow's headline: "Science proves fox says 'Phoebe'"

@bookslug2919

4 жыл бұрын

Fox News

Okay, that was amazing. "London + Japan - England = Tokyo"

@yshwgth

4 жыл бұрын

That needs to be a web site

@cheaterman49

4 жыл бұрын

More impressed by Santa + pig - oink = "ho ho ho"

@VoxAcies

4 жыл бұрын

This blew my mind. Doing math with meaning is amazing.

@erikbrendel3217

4 жыл бұрын

you mean Toyko!

@Dojan5

4 жыл бұрын

I was actually expecting New York when they added America. As a child I always thought New York was the capital of the U.S., I was at least around eight when I learned that it wasn't. Similarly, when people talk of Australia's cities, Canberra is rarely spoken of, but Sydney comes up a lot.

'fox' + 'says' = 'Phoebe' may be from newspapers quoting English actress Phoebe Fox

@skepticmoderate5790

4 жыл бұрын

Wow what a pull.

@rainbowevil

3 жыл бұрын

It was given ‘oink’ minus ‘pig’ plus ‘fox’ though, not fox + says. So we’d expect to see the same results as for cow & cat etc. of it “understanding” that we’re looking at the noises that the animals make. Obviously it’s not understanding, just an encoding of how those words appear near each other, but we end up with something remarkably similar to understanding.

Meanwhile in 2030: "human" + "oink oink" - "pig" = "pls let me go skynet"

I did this for my final project in my bsc. Its amazing. I found cider - apples + grapes = wine. My project attempted to use these relationships to build simulated societies and stories.

@Games-mw1wd

4 жыл бұрын

would you be willing to share a link? This seems really interesting.

@TOASTEngineer

4 жыл бұрын

Yeah, that sounds right up my alley, how well did it work

@ZoranRavic

4 жыл бұрын

Dammit Dean, you can't bait people with this kind of a project idea and not tell us how it went

@KnakuanaRka

4 жыл бұрын

You want to give some info as to how that went?

@blasttrash

Жыл бұрын

you are lying you did not do it. if you did, then paste the source(paper or code). - cunningham

EXTRA BITS NEEDED!

@kamalmanzukie

3 жыл бұрын

grow up

Fun points: A lot of the Word2vec concepts come from Tomáš Mikolov, a Czech scientist at Google. The Czech part is kinda important here - Czech, as a Slavic language, is very flective - you have a lot of different forms for a single word, dependent on its surroundings in a sentence. In some interview I read (that was in Czech and in a paid online newspaper, so I can't give a link), he mentioned that this inspired him a lot - you can see the words clustering by their grammatical properties when running on a Czech dataset and it's easier to reason about such changes when a significant portion of them is exposed visibly in the language itself (and learned as a child in school, because some basic parts of it are needed in order to write correctly).

@JDesrosiers

Жыл бұрын

very interesting

@afriedrich1452

Жыл бұрын

I keep wondering if I was the one who gave the inventor of Word2vec the idea of vectoring words 15 years ago. Probably not.

@notthedroidsyourelookingfo4026

Жыл бұрын

Now I wonder what would've happened if it had been a Chinese, where you don't have that at all!

@GuinessOriginal

Жыл бұрын

Wonder how this works with Japanese? Their token spaces must be much bigger and more complex

@newbie8051

Жыл бұрын

Technically you can share the link to the newspaper

This thing would ace the analogy section of the SAT. Apple is to tree as grape is to ______. model.most_similar_cosul(positive['tree', 'grape'], negative['apple']) = "vine"

Always love to see Rob Miles here!

@RobertMilesAI

4 жыл бұрын

@yondaime500

4 жыл бұрын

Even when the video doesn't have that "AAAHH" quality to it.

Foxes do chitter! But primarily they say "Phoebe"

I like this guy and his long sentences. It's nice to see somebody who can muster a coherent sentence of that length. So, if you run this (it's absurdly simple, right), but if you run this on a large enough data set and give it enough compute to actually perform really well, it ends up giving you for each word a vector (that's of length however many units you have in your hidden layer), for which the nearby-ness of those vectors expresses something meaningful about how similar the contexts are that those words appear in, and our assumption is that words that appear in similar contexts are similar words.

@thesecondislander

Жыл бұрын

His neural network has a very large context, evidently ;)

@MrAmgadHasan

Жыл бұрын

Imagine a conversation between him and D Trump.

'What does it mean for two words to be similar?' That is a philosophy lesson I am not ready for bro

@williamromero-auila7129

4 жыл бұрын

Breau

@_adi_dev_

4 жыл бұрын

How dare you assume my words meaning, don't you know its the current era

@cerebralm

4 жыл бұрын

that's kind of the great thing about computer science... you can take philosophical waffling and actually TEST it

@youteubakount4449

4 жыл бұрын

I'm not your bro, pal

@carlosemiliano00

4 жыл бұрын

@@cerebralm "Computer science is the continuation of logic by other means"

Today, vector databases are a revolution to AI models. This man was way ahead of time.

This was weirdly fascinating to me. I'm generally interested by most of the Computerphile videos, but this one really snagged something in my brain. I've got this odd combination of satisfaction and "Wait, really? That works?! Oh, wow!"

I am in love with this man's explanation! makes it so intuitive. I have a special respect for folks who can make a complex piece of science/math/computer_science into an abstract piece of art. RESPECT!

@nidavis

Жыл бұрын

"it's the friends you make along the way" lol

@sgttomas

Жыл бұрын

I was just thinking this and came to the comments…. Yup. Mr Miles is terrific. 🎉

@webgpu

Жыл бұрын

"complex" ? 🙂

@Commiehunter12

9 ай бұрын

He's Twerp. He's afraid to talk about X Y and XX Chromosomes and how we express them in language. shame on you

@subject8332

6 ай бұрын

@@Commiehunter12 No, he just didn't want to trigger the priesthood in a video about word embeddings but looks like he wasn't careful enough.

Rather than biggest city, it seems obvious it would be the most written about city, which may or may not be the same thing.

@packered

4 жыл бұрын

Yeah, I was going to say most famous cities. Still a very cool relationship

@oldvlognewtricks

4 жыл бұрын

Would be interested by the opposite approach: ‘Washington D.C. - America + Australia = Canberra’

@Okradoma

4 жыл бұрын

Toby Same here... I’m surprised they didn’t run that,

@tolep

3 жыл бұрын

Stock markets

I'm a simple man. I see Rob Miles, I click.

@koerel

4 жыл бұрын

I could listen to him all day!

This is basically node embedding from graph neural networks. Each sentence you use to train the it can be seen as a random walk in the graph that relates each world with each other. The number of words in the sentence can be seem as how long you walk from the node. Besides "word-vector arithmetics", one thing interesting to see would be to use this data to generate a graph of all the words and how they relate to each other. Than you could do network analysis with it, see for example, how many clusters of words and figure out what is their labels. Or label a few of them and let the graph try to predict the rest of them. Another interesting thing would be to try to embed sentences based on the embedding of words. For that you would get a sentence and train a function that maps points in the word space to points in the sentence space, by aggregating the word points some how. That way you could compare sentences that are close together. Then you can make sentences-vector arithmetics. This actually sounds like a cool project. I think I'm gonna give it a try.

@jamesjonnes

10 ай бұрын

How did it go?

Wow, that is mindblowing.

I'm a man of simple tastes. I see Rob Miles, I press the like button.

floats: some of the real numbers - Best description and explanation ever! - It encompasses all the problems and everything....

@RobertMilesAI

3 жыл бұрын

"A tastefully curated selection of the real numbers"

Rob Miles and computerphile thank you... IDK why youtube gave this gem back to me today (probably for my insesent searching for the latest LLM news these days) but I am greatful to you even more now than I was 4yrs ago... Thank you

This has suddenly become massively relevant 😅

Man, ... when AI will realize we can only imagine 3 dimensions, it will be so puzzled how we can do anything at all...

@overloader7900

3 жыл бұрын

Actually 2 spacial visual dimension with projection... Then we have time, sounds, smells...

@Democracy_Manifest

9 ай бұрын

The amount of neurons is more important than the experienced dimensions.

Word embedding is my favorite pass-time.

Love how you guys are just having fun with the model by the end

You really have a way with words, Rob. Please never stop what you do. ❤️

This was soooo interesting to me. I never dug deeper in how these networks work. But so many "Oh! That's how it is!". When I watched the video about GPT-2 and you he said that all the connections are just statistics, I just noted that internally as interesting and "makes sense" but didn't really get it. But with this video it clicked! So many interesting things, so thanks a lot for that. I love these videos. And seeing the math that can be done with these vectors is amazing! Wish I could like this more than once.

It makes so much more sense to represent words numerically rather than as collections of characters. That may be the way we write them, but the characters are just loose hints at pronunciation, which the model probably doesn't care about for meaning. And what would happen if a language model that relied on characters tried to learn a language that doesn't use that system of writing? Fascinating stuff.

I love the way he's discussing complicated topics. Thank you very much

OMG that ending. Love Robert's videos!

Phenomenal talk. Surprisingly compelling given the density of the topic. I really do hope they let this man out of prison one day.

I would suspect that this has to be very similar to how our own brains interpret languange, but then again evolution has a tendency to go about solving problems in very strange and inefficient ways.

@maxid87

4 жыл бұрын

Do you have examples? I am really curious - so far I always assumed nature does it the most efficient way possible.

@wkingston1248

4 жыл бұрын

@@maxid87 mammals have a nerve that goes from the brain to the throat, but due to changes in mammals it always goes under a vien in the heart then back up to the throat. This is so extreme that on a giraffe the nerve is like 9 feet long or something. In general evolution does a bad job at remmoving unnecessary features.

@Bellenchia

4 жыл бұрын

Clever Hans

@maxid87

4 жыл бұрын

@@wkingston1248 how do you know that this is inefficient? Might seem like that at first glance but maybe there is some deeper reason for it? Are there actual papers on this topic that answer the question?

@cmilkau

4 жыл бұрын

I doubt there is a lot of evolution at play in human language processing. It seems reasonable to assume that association (cat~dog) and decomposition (Tokyo = japanese + city) play an important role.

I'm surprised that there's been no mention of Rob's cufflinks in the comments for well over a year after upload

Mind blown, Thanks for the easy explanation. So calm and composed.

Very well done. I love the explanation. He obviously has deep insight to explain it so very well. Thanks.

This gotta be one of the best intuitive explanation of word2vec.

Beautifully simple explanation! Resplendent!

This page blows my mind. It takes you through the journey of thinking.

This blew my mind. Simply wonderful!

What’s with that room? Is this Prisonphiles?

@MichaelErskine

4 жыл бұрын

It's Nottinghack - but true it's a bit prison-like

So glad they allow this prisoner a conjugal visit to discuss these topics!

Mind blown, thank you very much for this explanation!

I am amazed and in love with his explanations. I just understand it clearly, you know.

super nice style of speaking, voice and phrasing. Good work !

I'm realllly curious about the basis vectors in this. What's the closest few words to etc..

@Guztav1337

4 жыл бұрын

That. Now I'm really curious.

@yugioh8810

4 жыл бұрын

I don't think that such reprenstation captures the distance information at all to begin with. The *closest* word is it has a distance of 1, (hamming distance in this case, I claim that each flipped bit counts as 1 hamming distance), but is not a word at all. Whereas in a vector-encoded representation since the words are mapped to a *vector space* then the closeness-farness of two vectors are conveyed in that representation. information representation if a fabulous topic I don't think I understand it yet. Information theory may help us understand information and information representation.

@Guztav1337

4 жыл бұрын

@worthy null , wtf are you on about? Nobody said anything about Hamming distance. He asked: what few words are the closest to the basis vectors [in euclidean distance] in that vector space.

@LEZAKKAZ

4 жыл бұрын

I see where youre going with your analogy, but embeddings generally dont work like that. At first all the words are randomly given a random vector and then those vectors change throughout the training process. So the words you're looking for would be meaningless in this case. If you're looking for the centroid word(words that appear in the center of the embeddings) then that would be words that have very broad contexts such as "the".

@StevenVanHorn

4 жыл бұрын

@Gerben van Straaten something that might be cute would be defining some human meaningful basis vectors then rotating/scaling the points to fit them. Then see what the remaining basises are. You're definitely right that they would not be human meaningful out of the box though

Beautiful concept. Thanks for sharing!

This is by far the best video I've seen on Machine Learning. So cool!!!

Very interesting. Would like to see more about these word vectors and how to use them.

This is very impressive. This is actually amazing.

16:20 Rob loves it, he's so excited by it 😄

This is fascinating! Might we be able to represent language in the abstract as a vector space? Furthermore, similar but slightly different words in different languages are represented by similar by slightly different vectors in this vector space?

Brilliantly explained! Thank you for this video

Mind blown... Able to do arithmetic on the meaning of words... I did not see that one coming :o A killer explanation on the subject thanks!! :D

Rob Miles is back :D

You could make a game with that, some kind of scrabble with random words, add and substract words to get other words. Maybe with the goal to get long words or specific words or get shortest or longest distance from a specific word.

absolutely fascinating

Amazing video! I appreciate every minute of your effort, really. Think back, wondering "Will anyone notice this? Fine, I'll do it." Yes, and thank you.

Oh yes, explaination and a concrete example

Would it be possible for Rob to share his colab notebook / code with us so we can play around with the model for ourselves? :D

@jeffreymiller2801

4 жыл бұрын

I'm pretty sure it's just the standard model that comes with gensim

@steefvanwinkel

4 жыл бұрын

See bdot02's comment above

Put 'politician' instead of Santa in the last example. Buy you a beer if it comes out as 'bleating'.

damn that's the best enjoyable informative video I've seen in a while

Very cool! I didn't know we could do word association to this degree.

word embeddings are the friends we make along the way

3rd result for dog is "bark incessantly." Even AI knows dogs are annoying mutants. Fun fact: Wolves don't bark, well, almost never.

@Dawn-hd5xx

4 жыл бұрын

Wild cats also don't meow. Even feral "domestic" (as in the species) cats don't meow, it's only towards humans that they do.

@NicknotNak

4 жыл бұрын

Duddino Gatto they mew. But they outgrow it pretty quickly. Humans don’t babble like babies when we grow up, but if that was the only think our feline overlords responded to, we would.

This video really deserves more views.

It'd have been nice to hear about the research craze around more sophisticated approaches to NLP. It's hard to keep up with the amount of publications lately related to achieving "state-of-the-art" models using GLUE's benchmark.

Wonderful explanation

best explanation about word embedding

Awesome explaining

I love that I have been thinking about modelling natural language for some time now, and this video basically confirms my way of heading. I have never heard of word embedding, but its exactly what I was looking for. Thank you computerphile and youtube!

How far we've come only 3 years later.

That was fascinating - thanks!

Thanks for a great explanation of word embeddings. Sometimes I need a review. I think I understand it, then after looking at the abstract, n-dimensional embedding space in ChatGPT and Variational Autoencoders, I forget about the basic word embeddings. At least it’s a simple 300-number vector per word, that describes most of the highest frequency neighboring words.

@michaelcharlesthearchangel

Жыл бұрын

Me too. I loved the review after looking how GPT4 and its code/autoencoder-set looks under the hood. I also had to investigate the keywords being used like "token" when we think about multi vector signifiers and the polysemiology of glyphic memorization made by these massive AI databases. Parameters for terms, words went from 300 to 300,000 to 300,000,000 to 1.5 trillion to ♾ infinite. Meaning: Pinecone and those who've reached infinite parameters have created the portal to a true self-learning operating system, self-aware AI.

That's just... amazing!

Nice thinkpad rob! I'm using the same version of x1 carbon with the touch bar as my daily machine. Great taste.

Would love sample code in cases like this where there’s a Jupyter notebook already laying about!

it's more than slightly surprising that you can explain this concept in 17 minutes, instead of going to a semester full of lectures.

@Rockyzach88

Жыл бұрын

Yeah but did you "learn" or just "understand while listening". Those are not the same things. Although, they may complement each other nicely in some cases.

When the room started getting brighter and brighter, I thought the rapture was happening xD

This is über amazing. I wonder if you could use that to predict cache hits and misses

3:00 pretty sure that graphic should've been just 2 points on the same line, given what he said a few sentences before that.

@panda4247

4 жыл бұрын

Yep, if the mapping of images is just taking the values each pixel and then making N-dimensional vector (where N is number of pixels), then the picture with more brightness would be the on the same line (if solid black pixels were still solid black, depending on your brightness filter applied).

Really nice explanation :)

Great explanation

Very informative!

Santa giving you "ho ho ho" was both terrifying and humorous at the same time. Wow.

Wow, that is really impressive!

If you train 2 networks with different languages I guess the latent space? would be similar. And the differences could be really relevant to how we thought differently due to using different language

This is amazing

I never thought the difference between "man" and "woman" could be so intertwined in a language! I can imagine it would make some people uneasy.

Plz more AI videos, they are awesome!

is the diagram with angles and arrows going off in all directions just for us to visualise it rather than how computers are looking at it, I didn't think they'd be calculating degrees. I thought it would be more about numbers of how close the match is like 0-100

The weights would be per-connection and independent of the input, so is the vector composed of the activation of each hidden layer node for a given input?

I think this looks more like an auto-encoder than GAN

@cmilkau

4 жыл бұрын

It's structurally the same as an AE, but it's trained differently. An AE has to reconstruct its input, but this network needs to find closely related, but different words.

This is awesome

What kind of news data set has the info that Santa says HOHOHO?

@RedwoodRhiadra

4 жыл бұрын

One that includes all the "human interest" fluff that newspapers publish around the holidays...

@blakef.8566

3 жыл бұрын

You mean HO_HO_HO

This is one of the coolest things i've seen in a while. Just thinking how small a neighbourhood of one word/vector should we take ? Or how does the implementation of context affect the choice of optimal neighbourhoods ?

@youssefezzeddine923

Ай бұрын

And contexts themselves vary from a person to another depending on how they experienced life. So it would be interesting to see also a set of optimal contexts and that would affect the whole thing.

Can you share the above colab notebook, it would be really great for a quick reference with the vid.

I kinda overlooked the importance of this video when it was released 3 yrs ago. not its basically the explanaition of how chatGPT does its thing... but with more data.