- 33
- 5 329 868
Artem Kirsanov
United States
Registrace 21. 04. 2018
I'm a computational neuroscience student and researcher. On this channel we seek to understand the brain and do deep explorations of interesting topics & papers from neuroscience (and related fields)
The Physics Of Associative Memory
Get 20% off at shortform.com/artem
In this video we will explore the concept of Hopfield networks - a foundational model of associative memory that underlies many important ideas in neuroscience and machine learning, such as Boltzmann machines and Dense associative memory.
Socials:
X/Twitter: x.com/ArtemKRSV
Patreon: www.patreon.com/artemkirsanov
OUTLINE:
00:00 Introduction
02:17 Protein folding paradox
04:23 Energy definition
08:25 Hopfield network architecture
14:03 Inference
18:40 Learning
22:48 Limitations & Perspective
24:43 Shortform
25:54 Outro
References:
1) Downing, K.L., 2023. Gradient expectations: structure, origins, and synthesis of predictive neural networks. The MIT Press, Cambridge, Massachusetts.
2) towardsdatascience.com/hopfield-networks-neural-memory-machines-4c94be821073
3) ml-jku.github.io/hopfield-layers/
Credits:
Protein folding: czcams.com/users/shortsfvBO3TqJ6FE
🎵 Music licensed from Lickd. The biggest mainstream and stock music platform for content creators
Viva La Vida by Coldplay, lickd.lnk.to/4aEPvoID License ID: RXj082JWjbA
Try Lickd FREE for 14 days for unlimited stock music and get 50% off your first mainstream track: app.lickd.co/r/47462149f85b4b6e9660bbe6d9b0f944
In this video we will explore the concept of Hopfield networks - a foundational model of associative memory that underlies many important ideas in neuroscience and machine learning, such as Boltzmann machines and Dense associative memory.
Socials:
X/Twitter: x.com/ArtemKRSV
Patreon: www.patreon.com/artemkirsanov
OUTLINE:
00:00 Introduction
02:17 Protein folding paradox
04:23 Energy definition
08:25 Hopfield network architecture
14:03 Inference
18:40 Learning
22:48 Limitations & Perspective
24:43 Shortform
25:54 Outro
References:
1) Downing, K.L., 2023. Gradient expectations: structure, origins, and synthesis of predictive neural networks. The MIT Press, Cambridge, Massachusetts.
2) towardsdatascience.com/hopfield-networks-neural-memory-machines-4c94be821073
3) ml-jku.github.io/hopfield-layers/
Credits:
Protein folding: czcams.com/users/shortsfvBO3TqJ6FE
🎵 Music licensed from Lickd. The biggest mainstream and stock music platform for content creators
Viva La Vida by Coldplay, lickd.lnk.to/4aEPvoID License ID: RXj082JWjbA
Try Lickd FREE for 14 days for unlimited stock music and get 50% off your first mainstream track: app.lickd.co/r/47462149f85b4b6e9660bbe6d9b0f944
zhlédnutí: 53 481
Video
The Most Important Algorithm in Machine Learning
zhlédnutí 347KPřed 3 měsíci
Shortform link: shortform.com/artem In this video we will talk about backpropagation - an algorithm powering the entire field of machine learning and try to derive it from first principles. OUTLINE: 00:00 Introduction 01:28 Historical background 02:50 Curve Fitting problem 06:26 Random vs guided adjustments 09:43 Derivatives 14:34 Gradient Descent 16:23 Higher dimensions 21:36 Chain Rule Intuit...
My Strategy To Consume Information Effectively
zhlédnutí 36KPřed 10 měsíci
For a FREE trial and 20% discount to Shortform go to shortform.com/artem And to download the Shortform AI browser extension, visit bit.ly/45DCpuM My name is Artem, I'm a neuroscience PhD student at NYU. In this video I talk about how I use summaries to consume knowledge from books and video lectures. Patreon: www.patreon.com/artemkirsanov Twitter: ArtemKRSV Github: github.com/ArtemK...
How I make science animations
zhlédnutí 705KPřed 11 měsíci
To try everything Brilliant has to offer-free-for a full 30 days, visit brilliant.org/ArtemKirsanov/ The first 200 of you will get 20% off Brilliant’s annual premium subscription. My name is Artem, I'm a neuroscience PhD student at NYU. In this long-requested video I share the creative process behind my videos - what software I use and break down some of my previous animations. Patreon: www.pat...
Building Blocks of Memory in the Brain
zhlédnutí 235KPřed rokem
To try everything Brilliant has to offer-free-for a full 30 days, visit brilliant.org/ArtemKirsanov/ The first 200 of you will get 20% off Brilliant’s annual premium subscription. My name is Artem, I'm a computational neuroscience student and researcher. In this video we discuss engrams - fundamental units of memory in the brain. We explore what engrams are, how memory is allocated, where it is...
Can We Build an Artificial Hippocampus?
zhlédnutí 196KPřed rokem
To try everything Brilliant has to offer-free-for a full 30 days, visit brilliant.org/ArtemKirsanov/ The first 200 of you will get 20% off Brilliant’s annual premium subscription. My name is Artem, I'm a computational neuroscience student and researcher. In this video we discuss the Tolman-Eichenbaum Machine - a computational model of a hippocampal formation, which unifies memory and spatial na...
How Your Brain Organizes Information
zhlédnutí 518KPřed rokem
To try everything Brilliant has to offer-free-for a full 30 days, visit brilliant.org/ArtemKirsanov/ The first 200 of you will get 20% off Brilliant’s annual premium subscription. My name is Artem, I'm a computational neuroscience student and researcher. In this video we talk about cognitive maps - internal models of outside world that the brain to generate flexible behavior that is generalized...
Brain Criticality - Optimizing Neural Computations
zhlédnutí 210KPřed rokem
To try everything Brilliant has to offer-free-for a full 30 days, visit brilliant.org/ArtemKirsanov/. The first 200 of you will get 20% off Brilliant’s annual premium subscription. My name is Artem, I'm a computational neuroscience student and researcher. In this video we talk about the concept of critical point - how the brain might optimize information processing by hovering near a phase tran...
Dendrites: Why Biological Neurons Are Deep Neural Networks
zhlédnutí 222KPřed rokem
Keep exploring at brilliant.org/ArtemKirsanov/ Get started for free, and hurry-the first 200 people get 20% off an annual premium subscription. My name is Artem, I'm a computational neuroscience student and researcher. In this video we will see why individual neurons essentially function like deep convolutional neural networks, equipped with insane information processing capabilities as well as...
A Map of Social Space in Your Brain
zhlédnutí 31KPřed rokem
Shortform link: shortform.com/artem My name is Artem, I'm a computational neuroscience student and researcher. In this video we talk about how hippocampus serves a "social map", representing information about conspecific individuals at different levels of abstraction. Patreon: www.patreon.com/artemkirsanov Twitter: ArtemKRSV OUTLINE: 00:00 Introduction 03:30 Overview of physical pla...
Theta rhythm: A Memory Clock
zhlédnutí 103KPřed rokem
Shortform link: shortform.com/artem My name is Artem, I'm a computational neuroscience student and researcher. In this video we talk about theta rhythm - a rhythmic pattern of brain activity (4-12 Hz), which is essential for memory encoding and retrieval. REFERENCES (in no particular order): 1. Hummos A, Nair SS. An integrative model of the intrinsic hippocampal theta rhythm. Lytton WW, editor....
Wavelets: a mathematical microscope
zhlédnutí 615KPřed rokem
Wavelet transform is an invaluable tool in signal processing, which has applications in a variety of fields - from hydrodynamics to neuroscience. This revolutionary method allows us to uncover structures, which are present in the signal but are hidden behind the noise. The key feature of wavelet transform is that it performs function decomposition in both time and frequency domains. In this vid...
Self-study computational neuroscience | Coding, Textbooks, Math
zhlédnutí 123KPřed 2 lety
Shortform link: shortform.com/artem This video is based on the article medium.com/neurotechx/how-to-get-started-in-computational-neuroscience-dde4b1817ccd My name is Artem, I'm a computational neuroscience student and researcher. In this video I share my experience on getting started with computational neuroscience. We will talk about programming languages, learning to code, recommended textboo...
Logarithmic nature of the brain 💡
zhlédnutí 225KPřed 2 lety
Shortform link: shortform.com/artem My name is Artem, I'm a computational neuroscience student and researcher. In this video we will talk about the fundamental role of lognormal distribution in neuroscience. First, we will derive it through Central Limit Theorem, and then explore how it support brain operations on many scales - from cells to perception. REFERENCES: 1.Buzsáki, G. & Mizuseki, K. ...
How to overcome study procrastination | 3 powerful tips
zhlédnutí 14KPřed 2 lety
Shortform link: shortform.com/artem In this video I'll talk about 3 amazing tips, which help you to overcome study procrastination. My name is Artem, I'm a computational neuroscience student and researcher. Socials: Twitter: ArtemKRSV OUTLINE: 00:00 Introduction 00:53 Shortform message 01:55 Why we procrastinate 03:10 Yin Yang technique 06:10 Time-based mindset 08:05 Spacing out 10:...
Your brain is moving along the surface of the torus 🤯
zhlédnutí 118KPřed 2 lety
Your brain is moving along the surface of the torus 🤯
My university note-taking | Zettelkasten & more
zhlédnutí 50KPřed 2 lety
My university note-taking | Zettelkasten & more
Memory Consolidation: Time Machine of the Brain
zhlédnutí 40KPřed 2 lety
Memory Consolidation: Time Machine of the Brain
Zettelkasten workflow for research papers | Zotero & Obsidian link
zhlédnutí 122KPřed 2 lety
Zettelkasten workflow for research papers | Zotero & Obsidian link
How to Effectively Teach Yourself ANYTHING
zhlédnutí 35KPřed 2 lety
How to Effectively Teach Yourself ANYTHING
Place cells: How your brain creates maps of abstract spaces
zhlédnutí 54KPřed 2 lety
Place cells: How your brain creates maps of abstract spaces
My simple note-taking setup | Zettelkasten in Obsidian | Step-by-step guide
zhlédnutí 679KPřed 2 lety
My simple note-taking setup | Zettelkasten in Obsidian | Step-by-step guide
How to read papers effectively | Research reading technique
zhlédnutí 34KPřed 2 lety
How to read papers effectively | Research reading technique
Mind mapping tutorial for students | Tips & Software
zhlédnutí 31KPřed 2 lety
Mind mapping tutorial for students | Tips & Software
How to choose a note-taking app | Zettelkasten | Notion vs Roam vs Obsidian
zhlédnutí 48KPřed 2 lety
How to choose a note-taking app | Zettelkasten | Notion vs Roam vs Obsidian
Neural manifolds - The Geometry of Behaviour
zhlédnutí 268KPřed 2 lety
Neural manifolds - The Geometry of Behaviour
Your brain CAN'T Multitask - Here's why
zhlédnutí 14KPřed 3 lety
Your brain CAN'T Multitask - Here's why
Interleaving vs Spaced repetition | Study hacks
zhlédnutí 20KPřed 3 lety
Interleaving vs Spaced repetition | Study hacks
Man, can you make your accent smoother
Guru of Fundamentals. I can't resist subscribing to your channel and watch all of your videos. The way you explained Chain Rule : the logic behind it is awesome. I am trying to visualize the Quotient Rule of Derivatives in your way. A good Teacher always makes you THINK 🙏
Thanks a lot for this intuitive video, I enjoyed to watch this, specially in dot product, I was confused why we use kernel trick in SVM and now I know it.
Is it only me or the background music selection is inspired by 3blue1brown just as well as the visuals and approach overall? For some reason I'm flashing back to 2021 when I binge-watched 3b1b, just by listening to the background. I know it's generic but not in sci-pop apparently.
what does "fourier transform is completely blind to time" even mean?! you can recover the original signal doing the inverse fourier transform: no loss of information
I'd click 'thumb up' a thousand times if I could, thanks a lot Artem!
спасибо, Артем)
Such a good video. Have liked and subscribed! I love the Curve Fitter 6000 machine in the animations to explain these concepts. Most textbooks are just too abstract and confusing but you have done a great job.
So, hard links exist in our brains.
Well, now I know how Trauma works. So, dealing with it as early as possible helps in the person not being able to develop it over time.
Your approach to trading is truly impressive. Thank you for teaching me so much!
Absolutely one of the best videos explaining data points and regression formulas I have ever seen. Amazing work
This is the best CZcams video I have ever seen. You explained everything masterfully! Thank you for giving my curiosity a vision, I’m so excited to explore more.
Thanks for this video. It's very educational and as said before here in the comments an easy-to-follow instruction to start with Obsidian and Zettelkasten. Also - I simply love the name you gave yours.
Very nice explanation.
The best explanation of machime learning i have ever seen on you tube ,amazing work .thank you👍
Best video I've ever watched about Obsidian. I'm really thankful for this content
The outro music 🙏🏻🙏🏻🙏🏻
Thanks for such a this amazing content
This video is actually the best I've found
tmi
MY DOUBT: Is it guaranteed that the loss function will always be a smooth well like hypersurface? Couldn't it have many local minima where we can get stuck?
Thank you for this video!
Why not the Hopf Vibration instead of a torus?
After getting a 10/10 in Calc II (Calc II is mutlivariable calculus in my country) I feel proud of myself for being able to skip most of this video because I immediately thought of the method and I was correct (even though I didn't learn it in uni)
How’d you do the animations?
Too long doing basic math - not what the title said - turned off.
can anyone please help explain why did he raise x1 to the power in 28:40 ?
Can you talk about attention mechanisme ?
Продал родину за бургеры
Its really too much helpfull to visualize and understand each and every thing
The replay goes in reverse order to allow back propagation.
Really good that you’re covering these foundational concepts of NNs. Cross-associative NNs, auto-associative NNs, and unsupervised learning are big missing pieces in today’s NNs.
This was one of the good oness. I really loved it and hope part 2 comes out sooner. Keep up the amazing production sir.
That excitatory and inhibitory connections remind me of statistical correlation function
Isn't the 2nd law of thermodynamics more directly linked to entropy? Is there an analog for entropy in the associative memory network?
Reminds me of gradient descent
That's because this is it.
The protein example got me thinking. Is there only one unique folded configuration of the lowest energy? Can there be multiple stable comfiguration anyway, and transitions between them?
This is really cool! Thanks for your work Artem!
This video is a gem.
Hello. It's been long since you last uploaded the last video. I hope you are well. Best videos, bro. Keep them coming 🎉
Thank you Artem Kirsanov for the incredible tool, I presented it to the entire physiological sciences department at my university
Man, you really nailed it, especially the Computational Graph and Autodiff part. I heard so many times about them in lectures on Stanford and others. However, this was impressive.
Good stuff!
чё за песенка там на русском?
Fabulous, bravo
Anyone else following the series? What do you think so far?
Artem!!! Is there any chance you've visualized feature engineering concepts like PCA, IPW, or weight of evidence encoding? Others have done it but your explanations are par-none ❤
Thanks!
Thanks!