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!
@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!
@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!
@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
29 күн бұрын
@@joeybasile1572it’s summer holiday
@ArtemKirsanov
29 күн бұрын
Wow, congrats!!
@SystemsMedicine
29 күн бұрын
Good Luck. And when things get tough, and they will… endeavor to persevere.
@holymoly54775
27 күн 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!
@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
29 күн бұрын
😮
@conduit242
24 күн 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
24 күн 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
17 күн 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.
@huytruonguic
25 күн 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
17 күн бұрын
theory of constructed emotion / active inference ;)
@theo4884
26 күн бұрын
Watching your "AI & Machine Learning" playlist feels like binge watching my favorite show. Hope you continue them. You are an amazing teacher
@owenpawling3956
Ай бұрын
So glad for another upload! You have no idea how fast I clicked!
@joonaskuusisto2767
29 күн 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
29 күн бұрын
Thank you!!
@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.
@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 :)
@JonRichie294
29 күн 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.
@kahvefincanim234
Ай бұрын
It is really great to visually explain such complex and valuable information in such an understandable way!
@scottmiller2591
28 күн 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.
@guillaumeleguludec8454
29 күн 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
@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!
@sirinath
25 күн бұрын
Can you do a course on Markov / Semi Markov / Hidden Markov / Semi Hidden Markov models please.
@victormanuel8767
6 күн бұрын
Fantastic. Absolutely phenomenal work here.
@AshifKhan-sn6jx
21 күн 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
@louisdupont2126
Ай бұрын
Man your videos are just awesome, and I finally understood the boltzman formula xD
@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
29 күн бұрын
Thanks! Good catch!
@darkyz543
25 күн бұрын
Marvelous. Thank you. I almost forgotten how delicious mathematic is.
@Jacob-ji1ec
Ай бұрын
This video is amazing man 🔥
@rxphi5382
26 күн 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
@iamdaddy962
26 күн бұрын
happy to see you in the US!! Hope you thrive here
@-mwolf
Ай бұрын
the 3b1b of neuroscience an ML, thx for the videos!
@nessiecz2006
25 күн 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;)
@AyushVerma-ui7re
Ай бұрын
beautiful explanation.
@anywallsocket
Ай бұрын
My 2nd physics class adjunct prof told me his fave subject was statistical physics, now I get it 🙏
@haroldhamburgler
23 күн бұрын
I've learn today, as many times before. Always finish the video before leaving an angry comment.
@English-bh1ng
Ай бұрын
I eventually grasped the notion of RBM. Thx
@enriquesolarte1164
Ай бұрын
Great videos
@luke.perkin.inventor
Ай бұрын
At 2x speed it sounded like you said "what sparked this sh*t" 😂
@syrachify
12 күн 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?
@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
@giuseppepapari7419
Ай бұрын
9:05 I guess you meant -ln p / epsilon = 1/T. But that is minor, I like the video
@nessiecz2006
25 күн бұрын
ive been searching for this comment, was wondering if im missing something. Thank you kind stranger
@ced1401
12 күн бұрын
Great video. There's a small typo around 9:15. ln(1/p)/epsilon would rather be 1/T.
@Darkev77
12 күн 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)?
@VaradMahashabde
29 күн бұрын
Best explainers, hands down
@SystemsMedicine
29 күн бұрын
Sweet Vid… Rock On!
@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
@ArbaouiBillel
28 күн бұрын
Amazing keep going 👍🏼
@Pedritox0953
16 күн бұрын
Great video!
@guyguy12385
Ай бұрын
yea you are absolutely goated
@justanotherytaccount1968
27 күн бұрын
Awesome video, thanks! Could the stochastic “hallucination” phase be related to hippocampal replay training cortical networks (“hidden” layer) during sleep?
@wwvvwvwvwvwv
Ай бұрын
me when ai learns to dream
@MlNECRAFT69
21 күн бұрын
lol the new title made me watch it again on accident😊
@leonardorazzai840
Ай бұрын
Wow, so fascinating 😍
@JuergenAschenbrenner
Ай бұрын
great stuff, keep up Your good work
@vinniepeterss
Ай бұрын
great video
@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.
@ThomasConover
25 күн бұрын
1:13 The Boltzmann machine is the AI equivalent of dropping acid for a human.
@daleanfer7449
Ай бұрын
great content❤❤❤
@davidfmendiola2009
27 күн бұрын
🙂¡Gracias!
@ArtemKirsanov
19 күн бұрын
🫶
@faisalsheikh7846
Ай бұрын
Wonderful❤
@InquilineKea
Ай бұрын
What temperature optimizes for the highest range of perplexity values?
@not_amanullah
Ай бұрын
Thanks ❤️
@notu483
24 күн бұрын
13:14 Softmax wasn’t mentioned?
@crazyedo9979
25 күн бұрын
Dr. Chandra. Will I dream?😁
@Rockamoley
2 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.
@polygondeath2361
25 күн 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.
@IoannisNousias
Ай бұрын
How do you create your animations? This is awesome.
@ArtemKirsanov
29 күн бұрын
After Effects + Python + Blender :) I have a video about it that might help: kzitem.info/news/bejne/2peXl2ebnpqYraQsi=EcoTIRW9Qhnnb9xS
@gunaysoni6792
Ай бұрын
I was expecting a Brilliant Sponsorship 😂
@chara2.o803
Ай бұрын
Lil bro is dreaming ❤
@maths.visualization
20 күн бұрын
Can You Share Video Code?
@cyb0rg14
Ай бұрын
I came here to learn about AI and going after understanding physics.
@mayankmanivyas9329
20 күн бұрын
+1
@1vEverybody
Ай бұрын
Ai learning how to dream is most people’s nightmare
@justanotherytaccount1968
27 күн бұрын
Extra comment for the algorithm
@car103d
Ай бұрын
HAL 9000: “Will I dream?”
@TeslaElonSpaceXFan
20 күн бұрын
👍
@futureshockpod
Ай бұрын
Holy crap this is hot.
@Arts_ng_sa_Socialismo
22 күн бұрын
Bonjour
@lost4468yt
Ай бұрын
When AI learns to meme?
@trucid2
Ай бұрын
Then I can retire. 🫡
@forblender2695
Ай бұрын
Me when ai drugs and hallucinates😅l😂😂
@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:)
@rangefreewords
29 күн 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
@kubaissen
Ай бұрын
Bug in step 2
@not_amanullah
Ай бұрын
🖤🤗
@jovanwatson7656
28 күн бұрын
Im lost
@bladekiller2766
Ай бұрын
How do these models compare to the SOTA like Transformers?
@nrao8977
29 күн бұрын
Dreams are NOT some non-existing "thing." In fact, they are a jumbled combination of events that have occurred. Thus, they are about "existing things." The human mind, when it dreams, is incapable of reasoning, unlike in the waking state. So, it uses events that have occurred and stitches a "dream." Simple.
@HadiLq
Ай бұрын
All good, but T=-\epsilon/|ln p|
@Japanology
Ай бұрын
Your voice sounds like your actual voice + AI trying to correct your English pronunciation. I personally prefer your natural voice :)
@ArtemKirsanov
Ай бұрын
hahaha, i can assure you that no AI was used :D
@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.
@BinaryDood
Ай бұрын
lets not fall into pareidolia please
@ericswain4177
Ай бұрын
AI still stands for Artificial Intelligence nothing more, so dreaming is still derived from an Artificial source. So if AI were to become sentient and Dream as we do then we as biological lifeforms would be no different than them in our progression from a once primitive state to what we are today in body and mind. ? Will AI someday procreate in some sense at some point riveling and or replacing biological humans. ? Would AI even take on a physical form, that of an animated android human simuloid ?
@vmartme
Ай бұрын
You start wrong.... AI generated Images are not creative at all they are taken form other just combined and that is not creativity either art. Looks stunning but is not creative. In our human history we had very few creative people even Picasso he stole from African natives tribes ideas. So when AI will be able think and create something without prompt input from people then we can call it creative now is just taking from others and combine together (stealing). For you guys who are not in "Visual Languege" whole life these images looks amazing but they are not. Is same for AI coding for unprofessional person look wow but for programmers with a lot experience look Okay.
Ай бұрын
You gave yourself the answer. AI is not creative, but human creativity is not what we all hype it to be. You are saying that it will be creative when it starts to produce things on its own. You are equating creativity and intelligence with consciousness. Those are not necessarily the same thing.
@lukebyer2592
Ай бұрын
The human brain does the same thing just in a much more complex way with a lot more inputs to play with and combine and take from.
@ShlomiOhayon
Ай бұрын
Do Androids Dream of Electric Sheep? :) en.wikipedia.org/wiki/Do_Androids_Dream_of_Electric_Sheep%3F
@BeCodeless-dot-net
Ай бұрын
Before I watch: Dreaming is just the brain trying to solve problems that we can see when we close our eyes because at this point we are not looking outward but inward. This is why we can day dream because dreaming never stops. Thus, computers cant dream. Animals can.
Пікірлер: 123