Join Shortform for awesome book guides and get 5 days of unlimited access! Get 20% off at shortform.com/artem
@vastabyss6496
Ай бұрын
First the Hopfield Network video and now this?! And only a month apart? I cannot thank you enough for the value that you've added to this platform
@ArtemKirsanov
Ай бұрын
Thank you!
@henrikjohnsson7403
Күн бұрын
Quick change of name! For a while, I thought you knew of the Prize in forehand when I scrolled through my list of "saved for later". And watched it now, awesome Work!
@KevinWang-jc1bx
Ай бұрын
AI's not the only one hallucinating, can't believe the rate and quality at which Artem is publishing these videos, thank you so much!
@vidal9747
Ай бұрын
I never knew my background in Physics would make understanding this topic such a breeze. It is bizarre how in this world areas that look so different can be so close.
@JohlBrown
Ай бұрын
i've never seen a well-worded explanation of temperature (as a casual ML enjoyer) but seeing the sigmoid morph with temperature and the relationship between stochastic and deterministic was such an awesome learning moment, thank you!
@ahaskarkarde4163
Күн бұрын
With the 2024 Nobel Prize in physics awarded to the pioneering works introducing the Hopfield Network and Boltzmann Machines, your latest videos explaining exactly these topics were just timely enough to help us build a great understanding of such important tools :)
@theo4884
Ай бұрын
Watching your "AI & Machine Learning" playlist feels like binge watching my favorite show. Hope you continue them. You are an amazing teacher
@holymoly54775
Ай бұрын
Hi Artem, I just want to say that in 3 weeks I begin my graduate degree in neuroscience, and it was your channel that inspired me to begin this journey two years ago. Keep up the good work, and I look forward to the inspiration for years to come.
@joeybasile1572
Ай бұрын
What classes are you taking right now?
@Sam264-n2o
Ай бұрын
@@joeybasile1572it’s summer holiday
@ArtemKirsanov
Ай бұрын
Wow, congrats!!
@SystemsMedicine
Ай бұрын
Good Luck. And when things get tough, and they will… endeavor to persevere.
@holymoly54775
Ай бұрын
@@joeybasile1572 I haven't started yet, but the program is non-traditional, where instead of registering for classes, there is a dedicated period for lectures everyday that will cover all aspects of neuroscience, followed by lab rotations and research training. Subjects included are neuroanatomy, computational modeling, molecular biology and neurogenetics, vision, audition, and then for the labs, there are courses in EEG, microscopy, and cytochemisty, and this is about half of all the subjects covered. It truly is a comprehensive program, which upon completion will feed me right into a PhD track depending on what areas I have excelled in. My background is in math and computer science, so I am hoping to focus on the computational side of things, but who knows where I will eventually end up!
@copywright5635
Ай бұрын
Always happy to watch your uploads. The Boltzmann distribution is something that I think is often misunderstood. So thank you for this video!
@huytruonguic
Ай бұрын
I get chills everytime someone tries to explain the differences between data's states and generator's states. The former is surface level while the later is highly abstracted. It says something about the many redundancies of the reality we live in and how there exists a general abstraction (math formalisms for example), or maybe that's just how we observe reality while being part of reality
@judehammoud5959
Ай бұрын
theory of constructed emotion / active inference ;)
@pandusonu
Күн бұрын
Good time to rename this video to "The generative model that won nobel prize in physics 2024"
@ArtemKirsanov
Күн бұрын
ahaha, good point!
@clayre839
Ай бұрын
The trouble with true creativity is intention. It's easy for humans to recognize things that we ourselves can produce and extrapolate patterns and impose experience and emotion on them but fundamentally if Randomness is the only thing driving the adaptation rather than transitive expression it is no more creative than a wind chime. You can think of it as the training data representing the tuning of each resonator and though we might FIND beauty in the emergent patterns, it is no more creative than its design and tuning, both requiring explicit human intervention. These models fed their own results very quickly deform into incomprehensible static
@clayre839
Ай бұрын
To add to this; the false equivalency and under emphasis of the human involvement in tuning is a large proponent of the demonstrably harmful supposition of replacing humans with machines; ignoring the value judgment that is imposed at every level of refinement. I deplore you to refrain from such false equivalencies as it's currently being used in attempts to undermine just about every creative field from engineering to writing to graphic design and would better be described as a sampling tool. These misconceptions have real world implications that are doing demonstrable societal harm. Take for example that even now I am fighting with the predictive text elements attempting to re orchestrate my unorthodox sentence structure and subsequently undermining the intent of my writing; that such a machine would have no insight into. It cannot understand meaning outside of Association and lacks any capability of truly understanding the emergent contradictions of language. So please stop describing these slot machines as creatives when its success is fundamentally built on confirmation bias.
@vinniepeterss
Ай бұрын
😮
@conduit242
Ай бұрын
Hilariously, your writing style is awkward and unnecessarily formal rather than creative. One would think computers would be just fine with such a style.
@clayre839
Ай бұрын
@@conduit242 for real, it's hard enough being autistic without my computer trying to fuck with me. We're both on the outside hear you'd think we'd be working together 🤣 but it's not the formality it's the variance that tends to fuck with predictive text. the tone was just to have assert a sincere formality to it. Like the larger issue of mechanization in Creative fields is a serious problem, full stop; and I think it's important the language we choose when we're talking about it
@unclicked4690
Ай бұрын
I love the wind chime analogy, that's a really cool conceptual analogy. I disagree with the basic premise that creativity requires intention, for example I'd say evolution is very creative but has no underlying "intention". It's also very well understood that human consciousness (and creativity) are fundamentally built on bias, indeed one can only learn if there is a bias to exploit. A very simple example of this is w.r.t identifying similarity of objects, we say a red cup is more similar to a blue cup than it is to a chair, however this requires a bias towards human every-day items. What I mean is that if we had to put a number on the similarity of blue cup and red cup, we could say they are 90% similar, while a chair is only 10%. Soon you run into trouble with this method, because how do you quantify how different a chair and a cup are from the ocean? what about a crimson cup? what about bacteria? what about a black hole? What about a cermanic red cup? What you see is that you need ever increasing detail, and you metric of similarity simply explodes or collapses to non-sense. Humans exploit bias to be able to think, to be able to logically classify items and objects and produce creative solutions.
@etunimenisukunimeni1302
Ай бұрын
You have a knack to explain things in an understandable way without dumbing them down too much, thanks! Finally I know what the temperature setting actually does in a neural network, funny how analoguous it is to physical temperature :)
@vladimirputin7443
Ай бұрын
This guy is awesome. I can't explain how much more intelligent I feel after watching your video. Thank you so much for taking out time to educate people like us.
@owenpawling3956
Ай бұрын
So glad for another upload! You have no idea how fast I clicked!
@scottmiller2591
Ай бұрын
This video was one of the bright spots of my day. It was well-crafted, reminded me of my work on ladder RBMs long, long ago, and got me thinking about how modern machines could build on these methods, and vice versa.
@joonaskuusisto2767
Ай бұрын
This is incredible stuff once again. You have pretty much covered everything I’m interested in neuroscience with insight I never possesed. I researched brain criticality and modeling but now on a boring day job. Glad we have people like you!
@ArtemKirsanov
Ай бұрын
Thank you!!
@JonRichie294
Ай бұрын
This is insane! I love your videos on this channel! I’m just waiting for your channel to exponentially boom to a million subscribers.
@guillaumeleguludec8454
Ай бұрын
Wow you really nicely explained what Boltzmann machines are and where they come from, and the animation in super pretty ! Thank you Mr Kirsanov
@kahvefincanim234
Ай бұрын
It is really great to visually explain such complex and valuable information in such an understandable way!
@AshifKhan-sn6jx
Ай бұрын
Okay, you taught me about boltzman distribution better than my school physics teacher and it wasn't even the main point of what you were trying to do
@imaltenhause4499
Ай бұрын
Fantastic video. A small typo however at 08:41. There you denote -ln[p]/epsilon = T. It should be: -epsilon/ln[p] = T.
@ArtemKirsanov
Ай бұрын
Thanks! Good catch!
@raajchatterjee3901
7 күн бұрын
Is this the relationship that relates temperature with differentials of energy and entropy?
@ItsGlizda
Ай бұрын
I recently stumbled upon your channel, and it's absolutely fascinating! It ignites my curiosity and explains things in a way that awakens my inner child. Keep up the fantastic work!
@ArtemKirsanov
Ай бұрын
Wow, thank you so much!
@victormanuel8767
Ай бұрын
Fantastic. Absolutely phenomenal work here.
@sirinath
Ай бұрын
Can you do a course on Markov / Semi Markov / Hidden Markov / Semi Hidden Markov models please.
@BinghaoWang-k5b
3 күн бұрын
amazing, detailed and easy to understand. thank you so much
@iamdaddy962
Ай бұрын
happy to see you in the US!! Hope you thrive here
@AyushVerma-ui7re
Ай бұрын
beautiful explanation.
@darkyz543
Ай бұрын
Marvelous. Thank you. I almost forgotten how delicious mathematic is.
@rxphi5382
Ай бұрын
I like the passion I feel from you in your videos! I just wanted to inform you that there is am small typo at 15:06 in the bottom right corner
@English-bh1ng
Ай бұрын
I eventually grasped the notion of RBM. Thx
@anywallsocket
Ай бұрын
My 2nd physics class adjunct prof told me his fave subject was statistical physics, now I get it 🙏
@ced1401
Ай бұрын
Great video. There's a small typo around 9:15. ln(1/p)/epsilon would rather be 1/T.
@Jacob-ji1ec
Ай бұрын
This video is amazing man 🔥
@anywallsocket
Ай бұрын
What you could do for visualization is plot a distribution of x for the digits above them like a mountain that looks like an 8 is different from that of a 2 etc
@catcatcatcatcatcatcatcatcatca
Ай бұрын
0:23 oh god. Reading that chatGPT answer hurts. That is equivalent to asking for a pasta recipe and seeing the answer starting with 1) start a greasefire in the kettle 2) for eight to ten minutes, pour water on it
@VaradMahashabde
Ай бұрын
Best explainers, hands down
@haroldhamburgler
Ай бұрын
I've learn today, as many times before. Always finish the video before leaving an angry comment.
@syrachify
Ай бұрын
Awesome video! I love this channel! I have a question, which I hope someone will clarify for me: if Boltzmann Machines are unsupervised, how do we know what data is meaningful (like number digits) and what data is just noise, so that we sculpt valleys around the meaningful patterns in the energy landscape? Similarly, in the weight update rule: updating iteratively works on maximizing the probability of the training data, equivalent to minimizing the energy of patterns, but the rule itself assumes we have to know beforehand what the patterns are (because of data - model). Can anyone help with an answer?
@louisdupont2126
Ай бұрын
Man your videos are just awesome, and I finally understood the boltzman formula xD
@enriquesolarte1164
Ай бұрын
Great videos
@luke.perkin.inventor
Ай бұрын
At 2x speed it sounded like you said "what sparked this sh*t" 😂
@CopperKettle
Күн бұрын
Thank you, this is very interesting. Keep up the good work.
@nessiecz2006
Ай бұрын
I was worried i was missing something at 8:43 . Nevertheless, great vid, gonna continue watching now:) Thank you for making these explanations PS: appreciate the 3b1b music and style;)
@yacinebel-hadj6559
13 күн бұрын
Thanks amazing work I love this topic :)
@ralvarezb78
2 күн бұрын
14:00 This is strongly related to simulated annealing optimizacion method
@vidal9747
Ай бұрын
Our brains activate neurons based on probabilities. Those are created by particles that follow laws pretty close to what is explored in thermodynamics and statistical mechanics. There is nothing more fitting than creating models that tend to mimic those aspects. Our computers are absolutely better than humans for problems we already know the equations. Because we know the uncertainty of every number in a computer. But for new problems, a probabilistic approach is very good.
@WillyDarko
23 сағат бұрын
Insanely high quality content
@-mwolf
Ай бұрын
the 3b1b of neuroscience an ML, thx for the videos!
@giuseppepapari7419
Ай бұрын
9:05 I guess you meant -ln p / epsilon = 1/T. But that is minor, I like the video
@nessiecz2006
Ай бұрын
ive been searching for this comment, was wondering if im missing something. Thank you kind stranger
@Darkev77
Ай бұрын
Given our current understanding of Quantum Mechanics and energy levels being quantized, is the statement @8:08 true (is it constant with the same amount)?
@justanotherytaccount1968
Ай бұрын
Awesome video, thanks! Could the stochastic “hallucination” phase be related to hippocampal replay training cortical networks (“hidden” layer) during sleep?
@Pedritox0953
Ай бұрын
Great video!
@SystemsMedicine
Ай бұрын
Sweet Vid… Rock On!
@SeattleShelby
21 күн бұрын
As a Boltzmann Brain in a fever dream, I found this video very insightful into my waking nightmare.
@leonardorazzai840
Ай бұрын
Wow, so fascinating 😍
@ArbaouiBillel
Ай бұрын
Amazing keep going 👍🏼
@wwvvwvwvwvwv
Ай бұрын
me when ai learns to dream
@guyguy12385
Ай бұрын
yea you are absolutely goated
@vinniepeterss
Ай бұрын
great video
@JuergenAschenbrenner
Ай бұрын
great stuff, keep up Your good work
@daleanfer7449
Ай бұрын
great content❤❤❤
@ThomasConover
Ай бұрын
1:13 The Boltzmann machine is the AI equivalent of dropping acid for a human.
@peterpetroff851
22 күн бұрын
20:47 spelling error. Thank you
@MlNECRAFT69
Ай бұрын
lol the new title made me watch it again on accident😊
@gunaysoni6792
Ай бұрын
I was expecting a Brilliant Sponsorship 😂
@1vEverybody
Ай бұрын
Ai learning how to dream is most people’s nightmare
@davidfmendiola2009
Ай бұрын
🙂¡Gracias!
@ArtemKirsanov
Ай бұрын
🫶
@not_amanullah
Ай бұрын
Thanks ❤️
@InquilineKea
Ай бұрын
What temperature optimizes for the highest range of perplexity values?
@IoannisNousias
Ай бұрын
How do you create your animations? This is awesome.
@ArtemKirsanov
Ай бұрын
After Effects + Python + Blender :) I have a video about it that might help: kzitem.info/news/bejne/2peXl2ebnpqYraQsi=EcoTIRW9Qhnnb9xS
@crazyedo9979
Ай бұрын
Dr. Chandra. Will I dream?😁
@notu483
Ай бұрын
13:14 Softmax wasn’t mentioned?
@Arts_ng_sa_Socialismo
Ай бұрын
Bonjour
@ronnysanjaya6823
19 күн бұрын
Yes many thanks.
@car103d
Ай бұрын
HAL 9000: “Will I dream?”
@TeslaElonSpaceXFan
Ай бұрын
👍
@faisalsheikh7846
Ай бұрын
Wonderful❤
@Rockamoley
29 күн бұрын
This is a good video, but the history given in the first few minutes is completely hallucinated. Associative memories are as old as van Neumann architectures, and thinking like humans has always been the first goal of researchers. Calculating exact trajectories was a useful stepping stone.
@stathius
18 күн бұрын
How realistic is the assumption that the probability of jumping between any adjacent state is equal?
@SaúlAlejandroVillaradosFlores
8 күн бұрын
I fn Love ur channel buddie
@chara2.o803
Ай бұрын
Lil bro is dreaming ❤
@idegteke
Ай бұрын
The fact that some people might even consider the idea that the IA we know of has any kind of own intelligence or capability of creating novum shows that the people creating and marketing it from behind are really good at what they are doing... at making money:)
@cyb0rg14
Ай бұрын
I came here to learn about AI and going after understanding physics.
@mayankmanivyas9329
Ай бұрын
+1
@polygondeath2361
Ай бұрын
We can reject the premise right off the bat. There really isn't much ambiguity when it comes to AI "art". It is algorithmic and soulless. There wasn't a shift from algorithmic to creative; as it stands, machines are yet to be creative, and have stuck to being algorithmic.
@Singularity606
3 күн бұрын
Only person in the comments to lash out in this way, parroting the most boring meme of them all ("soulless").
@polygondeath2361
3 күн бұрын
@@Singularity606 I can appreciate the vast applications of machine learning technologies. Art isn't one of them. It's hard to not tell when AI is involved in any "creative" capacity. Thus, soulless.
@maths.visualization
Ай бұрын
Can You Share Video Code?
@futureshockpod
Ай бұрын
Holy crap this is hot.
@justanotherytaccount1968
Ай бұрын
Extra comment for the algorithm
@lost4468yt
Ай бұрын
When AI learns to meme?
@trucid2
Ай бұрын
Then I can retire. 🫡
@高煜朗
23 күн бұрын
someone is stealing your video in chinese website: bilibili
@HaicangChen
Күн бұрын
Would be interesting to see the # views of these days...
@kubaissen
Ай бұрын
Bug in step 2
@bladekiller2766
Ай бұрын
How do these models compare to the SOTA like Transformers?
@ericswain4177
Ай бұрын
AI Learns to Dreaming is a fallacy as Dreamig is not a Learned phenomenon to start with, We as humans don't even know what dreams are or where they come from so there is nothing for AI to emulate.
@rangefreewords
Ай бұрын
If a machine learning ESP knew I what I was thinking about headgear and breathing underwater one day ahead' of my father's head burried under in a pond. lmk. I only thought about it. I could only randomly find a half japanese/ half italian woman one-three days before I ever met her in 2008. But, if your cognitive ability is more than one day. LMK
Пікірлер: 142