Dendrites: Why Biological Neurons Are Deep Neural Networks

[@ArtemKirsanov]

Keep exploring at brilliant.org/ArtemKirsanov/ Get started for free, and hurry-the first 200 people get 20% off an annual premium subscription.

[@tetrahexo5592]

Hey, I love your unique work😁👍, may i ask you if would you like someday explain the basics of synapse plasticity in biological neuron networks?

[@JohnSmith-ut5th]

I developed a theory about 15 years ago that neurons actually function more like mathematical group permutations than anything else. Their goal is to organize and group action potentials from synapses (putting similar action potentials closer together in time prior to integration). I actually developed C code to show how they can be used to solve a 50 node 2D Hamiltonian path problem extremely fast (in C it was solved almost instantly). The behavior of individual neuron dendritic growth was modeled by a genetic algorithm. I never published my research, so anyone is welcome to try and reproduce this.

[@aissahoi7308]

Like the video.♥️♥️ Can anyone tell me what software has been used for the animations?🙏🏻🙏🏻

[@mattaku9430]

On the interesting note: We don’t just have static weights, we also have fast weights, they’re dynamic and decay fast

[@agrymakismanolis7925]

Neuroscience PhD student here. Having followed this topic, although from a distance, since I am more into molecular neurobiology, I must say you did a very good job of explaining this very interesting topic. I have been in lectures from some of the researchers you included and I have to say I understood way more things from you than I did before. Thank you!

[@ArtemKirsanov]

Wow, thank you so much! It's really nice to hear that!

[@zakiyo6109]

researchers are not teachers i dont know why universities haven’t understood that yet.

[@Caius1930]

​@@zakiyo6109 especially so at top universities. They're mostly hired for the funding and citations they can attract rather than teaching ability...

[@michelstronguin6974]

Sparse distributed representation (thousand brains theory) from Numenta is more accurate since it’s based on actual biological data.

[@JiroMusik]

I saw another video here on yt where one was talking about a study showing consciousness is just a download. Pretty sure in

[@ramotimeramotude6448]

I have a PhD from Berkeley in neuro & engineering, currently work in ML, and you break this stuff down really well. I love the digested summary of the paper equating a neuron to a small CNN. Thanks, and keep it up man

[@cdreid9999]

i envy you so much. I never had your opportunities but i wanted to do ai research as a programmerin the 80s. It was learning the most basic parts of neuroscience that showes me (and others) how we wpuld achieve it. Unfortunately it also helped me understand how we needed huge leaps in processing power to get there. It is amazing seeing real ai coming to fruition in my lifetime

[@ArtemKirsanov]

Thank you!

[@mofo78536]

I feel like the insight that each neuron is essentially like a small CNN function would actually be a useful intuition for better neural hardware accelerations if we could keep the numbers of large distances connected between neurons down. Much like how software design to be multithreaded is better for multicore CPUs.

[@mikip3242]

This is crazy-interesting stuff. The whole thing reminds me of the development of the concept of atoms. Atoms were supposedly meant to be the indivisible building blocks of matter from which you could build anything. The greek concept was adapted to what we now call...well.... atoms. The problem is that atoms are not elementary building blocks and as it turns out they are complex systems made of multiple more fundamental particles that can be arranged in many many ways to build many atoms in very different states and configurations. So the real greek concept of "atom" should be applied to fundamental particles of the standard model, and what we call atoms should be renamed. The same goes for neurons. In AI a "neuron" is just the smallest conceivable operational unit that you can use to build more complicated logic systems. Historically we thought that biological neurons were just that, the smallest indivisible element of logic (a simple lightbulb, a binary switch), but then, like when we splitted the "atom", we discovered that in fact a biological neuron is really equivalent to an ensamble of more simple logic gates. So, the actual "atoms of logic", the neurons in neural networks, should not be confused with neurons in biology.

[@ArtemKirsanov]

Wow, this is actually fascinating insight!! I've never thought about it

[@mikip3242]

@@ArtemKirsanov By the way, your explanation of the perceptron was one of the best I've ever seen. Clear, straight to the point and esthetically pleasing. Congratulations for the awesome chanel.

[@starxcrossed]

We’re computers made of computers

[@andrewdunbar828]

In general, all science and discovery is fractal-shaped. The picture is never complete because the more you zoom in the more details there are and you realize everything you saw before zooming was just an approximation.

[@jamescheddar4896]

they're called elements when they're atoms so a single elementoid?

[@HeduAI]

This content is exceptional! As an AI engineer with limited biology training, I previously felt so overwhelmed by the complex terminology and extraneous information in the realm of neuroscience. Then struck gold by discovering your channel. Thank you!

[@corsaircaruso471]

I’m a fine arts doctorate with only 6 or so credit hours of formal education in science post-high school. You were able to make this topic at least comprehensible for me. Thanks for the engaging format!

[@ArtemKirsanov]

Thank you! I'm glad you enjoyed it :)

[@your_-_mom]

What job are you looking for

[@Afkmuds]

@@your_-_mom petridish

[@Gluatamat]

In the problem of approximation of the XOR-function, the choice of the activation function not step-func but П-shaped allows us to solve that by just one single neuron. Then the input space will be divided into 3 parts (- + -). The choice of activation function in ANN plays a significant role. In the SIREN family of models, periodic sin cos functions are generally used. And it allows you to encode the input vectors in hierarchy of scales at once

[@ArtemKirsanov]

This is interesting! I've never heard about SIREN networks before (or any model that uses periodic activation functions for that matter). I was really impressed by their results presented in this video kzbin.info/www/bejne/h2PJfYp9d8qUn6s Thank you for pointing it out!

[@Simulera]

There is a small record of work done at Los Alamos from the late 80’s through the 90s using “radial basis functions”, which are a specific kind of non-monotone activation functions, in adaptive learning NNs. Although not precisely what was used, an erf or ndf is an example of what was used, as opposed to the square wave you mention, but all the same in one sense. Specifically they were useful for both reduction of layers in NN for a given learning task and also, obviously, for logical non-monotonicity such as classically found in the XOR-perceptron problem. But in addition, it seemed and still seems to me that since with real neurons, if you continue to drive them past threshold, the outputs saturate and decline as a function of input values, we find non monotonic activation in a natural way, built in. And it’s computationally useful as well as “nonlinear” and all that stuff. So radial basis functions, periodic ones, even varying ones perhaps, are important and extend basic computational power. It takes some of the network modeling and moves in “inside” that’s true enough, for good or bad. But it potentially extends what is possible to do on a given “budget”. It doesn’t help that much with other things that remain problematic for brute-force ML or DL. Interesting times.

[@lythd]

i wonder if that would reduce the amount of layers required in that model to approximate the neuron

[@jumpstar9000]

Very interesting observation. Seems like this could be modeled with an appropriate basis function. At first blush, kind of reminds me of spherical harmonics transfer functions in computer graphics I'm a computer scientist, so grabbing something that I have seen before. Very interesting stuff, thank you.

[@jumpstar9000]

@@Simulera Hah, excellent info about these radial basis functions. I had just typed about spherical harmonic transfer functions and then read your comment. Definitely mind is ticking over. Thanks for sharing this golden nugget.

[@tedarcher9120]

Depolarisation is decreasing voltage but increasing potential. Slight correction by a physicist there ;)

[@stafan102938]

But if a neuron sits at a negative value in its resting state, surely its the other way round. Voltage gets closer to 0 so increases but potential decreases?

[@tedarcher9120]

@@stafan102938 voltage is just a potential difference so it is a matter of labeling. It makes more sense to use it in absolute terms in this case

[@stafan102938]

@@tedarcher9120 But regardless of using negative or positive voltages to talk about it, a depolarisation would always refer to a reduction in potential across the membrane. Plus the voltage value falls out of an equation which uses ion concentrations to calculate it, so that's why its consistently referred to as negative inside the cell and positive outside.

[@stafan102938]

@@tedarcher9120 Maybe I've just the terminology backwards in my understanding of it all though

[@stafan102938]

@@tedarcher9120 Going to blame my school physics teacher for giving cop out answers to explaining voltage and potential

[@bradmesser4807]

Former Big Tech AI engineer & Researcher. Love what you have to say here. A learned a lot about the neuroscience perspective of what we do. Thanks for sharing!

[@tantzer6113]

Showing that it takes a 5-layer neutral network to capture the full range of responses to all possible inputs in a dendritic neuron is not the same as showing that a dendritic neuron has the same learning capacity as a trainable five-layer deep neural network. It seems a bunch of hidden assumptions are involved in making that inference. One can easily imagine a non-linear, complex system where one would need multiple layers to describe its input- output behavior even though the complex system in question has zero ability to learn anything. Perhaps the take-away of these papers is not that individual neurons have the learning power of a general untrained 5-layer network, but that they can do the function of a trained 5-layer network that does XOR or something like that. Also, “can” is not the same as “does.” Five layers were needed to capture the full range of possible inputs to the neuron, but in practice the range of inputs might be much narrower than all the inputs imagined via mathematical simulation.

[@lucascsrs2581]

Awesome content. It's always amazing to see someone that can explain advanced topics in terms that even who are not familiar with the field can understand. Fascinating stuff.

[@FriedChairs]

While I didn’t understand most of it I subscribed just because I can appreciate the value he is providing for free with this content.

[@MrMikkyn]

The all of the animations on this are amazing. I love them. They make neurons look so colourful and exciting, and its really engaging. I'm still a beginner at neuroscience but I really like both topics of neural networks in machine learning and computational neuroscience, so this video is perfect for me. I will definitely rewatch it.

[@DiegoGonzalez-gb3ct]

I just cannot explain the fascination, love, and inspiration that this video delivers.

[@casey7882]

As an undergraduate who is currently studying to go into computational neuroscience, I feel privileged that such a high quality channel exists for a relatively niche subject like this. Keep up the good work!

[@ConnoisseurOfExistence]

Superb video! I'm a first year Data Science and Neuroscience uni student (aged 38) and am very interested in the fusion of these 2 fields. Will come back to this video again to share some thoughts later. Anyway, even if all the functionality of the human biological neural networks and neurons isn't currently fully implemented in artificial neural networks, it doesn't mean that it won't be in the near future. Also, as you point out here, the same functionality is also achievable by deep neural nets, it's just a matter of efficiency.

[@sergeantoreo8062]

Wait, your doing a university course that integrates both data science and neuroscience togather? and if it is or isn't, its still cool that your doing both.

[@ConnoisseurOfExistence]

@@sergeantoreo8062 The uni that I'm at specializes in double degrees like that. There's data science and physics for example, or psychology and neuroscience, literature and music, and so on.

[@marvin.marciano]

@@ConnoisseurOfExistence such a lucky guy... i wish i could do that. I'm from Brazil and i'm also super interested in such topic, although we don't have that much of investment in these areas, especially in cities in the middle of nothing. I hope you have a great time while in this course.

[@ConnoisseurOfExistence]

@@marvin.marciano Thanks. Why don't you apply in the capital, or another country? You speak English. I'm not studying in my own country at the moment...

[@marvin.marciano]

@@ConnoisseurOfExistence maybe when I get older, it turns out to be more viable than it is now. I'm currently at computer science graduation

[@magnuswahlstrom766]

Fascinating. Especially the idea that neurons are sensitive to the activation order of signals along its dendrites. I remember seeing a talk long ago where the speaker was discussing what aspects of the brain's (or the neurons') configuration that are actually coded for in our genes, and argued that (a) almost none of the neuron-to-neuron connections or connectivity strengths are controlled (as you may have thought they were, if the brain was a giant network of threshold gates), but (b) great care is taken to control, across a large variation of different neuron cell types, precisely where along the dendrite each nerve cell type connects and in what manner (which makes no sense in a threshold gate model). That seems rather more on-point with the model you're describing!

[@13lacle]

Great video, It's cool that single neurons can act as their own mini deep neural networks. I think that it is worth clarifying that even though the biological neurons are not equivalent to perceptron neurons in function, all this does is move the perceptron to a sub part of the neuron. Meaning that the fundamental principle is the same (ie. a network of sub networks is still a single network on the whole)

[@gjuhn]

This was fantastic - easy to follow and amazing production quality. I was wondering how you do your animations, but I see you have a video for that too! I want to go through all of them!

[@mgostIH]

I loved this! It gives a very optimistic outlook to that artificial neural networks can at the very least simulate our own neurons if they need it to solve a problem. It's important to notice that while a deep neural network can approximate a single biological neuron with a lot of layers and parameters, this only provides an upper bound on the total amount of parameters you'd need to approximate multiple biological neurons! Not only may there be a more efficient architecture the authors haven't tried, but it may be that as artificial neural networks scale to become larger they become more efficient at handling the equivalent of an individual biological neuron. This because the overall behaviour of a system may be simpler to model by exploiting correlations and limiting behavior, just like a glass of water with respect to all of the H2O molecules composing it.

[@revimfadli4666]

Sounds like what Sandler, Kirsch, and Schmidhuber have tried to do with promising results

[@moormanjean5636]

Yes its very likely that your second explanation is at play. Grasping the function of a neuron with active dendrites would be much easier when the dimension of the computational manifold is scaled up.

[@StanislavMudrets]

Neurons don't get put together like a "neural net". They start out as whole undifferentiated cells and then progressively specialize into neurons. Neural nets are put together like machines - from combination of separate parts, components, functions, etc. according to a plan. In other words, although neural nets can simulate some abstract aspect of neurons that might interest humans, you can't really understand neurons using neural nets. For example, neural nets don't socialize. They don't generate projections and try to make it in neuron society, etc. It's kinda like studying humans using speech recognition software that's incapable of going out and making friendships, looking for work on its own, trying to find a spouse, etc.

[@revimfadli4666]

@@StanislavMudrets would graph convolution or attention be enough socialisation?

[@StanislavMudrets]

@@revimfadli4666 Is this activity planned by a researcher or something that a bunch of math functions just decided to do on their own? Math functions performing other's will don't do anything spontaneously for their own purposes. They are completely parasitic on human purpose.

[@matveyshishov]

Always looking forward to your videos, thank you for your hard work! A few questions (maybe answered in the papers, I haven't read them yet): * One neuron is great, how much do we know about the next level, a net of several neurons? IIRC, the number of different neurotransmitters is in many thousands? How does it change the compute? Does it mean we need to create a 5-8 layer nn for every MODE a neuron finds itself in or smth? * Dendritic spines. Neuroplasticity. Has it been incorporated into the simulation models yet? * On a tangential, have you looked at Michael Levin's research? Starting to look like neurons are but a special case of bioelectric signaling.

[@moormanjean5636]

1. I'm not sure if the number of neurotransmitter types would number in the thousands. For context, serotonin, one of the most complex neurotransmitters (i.e. more diverse receptor class) has about 40 types of receptor types, which around 7 major subclasses. Acetylecholine, which I believe is the most complicated, has upwards of 200 receptor types IIRC. Importantly, a specific neuron doesn't have to express all receptor types for all neurotransmitters, and are likely specialized for their specific role in the circuit, i.e. what specific neurotransmitters they receive. Thus, some neurons may be much more computationally complex than others, at least in terms of receptor subtypes / neurotransmitters received. To simplify this to a 5-8 layer nn is not trivial, as as having a 8 layer temporal CNN for each node in your network is not computationally feasible. 2. I am sure that dendritic spines have been incorporated into simulation models, you may want to look into the dendritic neuron model and active dendrite research in general. As far as neuroplasticity, I would argue that backprop implements a version of plasticity, i.e. plasticity = weight changes. If you are talking about spike timing dependent plasticity (STDP) or behavioral time scale plascity (BTSP), I would assume there are also models which incorporate them.

[@ArtemKirsanov]

Wow, thank you very much, Matvey! 1) The number of different neurotransmitters is actually much lower than that - less than a hundred. It is true, that there are any subtypes of receptors to a single neurotransmitter, which differ in kinetics (how fast they open), sensitivity, ion selectivity, etc. It is not clear how to incorporate such diversity into network models, so, usually people just interconnect neurons with different synapses, explicitly defined by maximum conductances (either excitatory or inhibitory) and time constants. It’s worth saying, however, that certain compounds, such as serotonin, dopamine, norepinephrine can act more globally (as neuromodulators), affecting a large population of neurons simultaneously and modulating their excitability. There are certainly models that incorporate neuromodulation, but again, in a very simplified description (e.g. introducing an additional current, which reflects the activation of extrasynaptic receptors). This approach with describing a single neuron with a neural network is very new and I don’t know any papers that model a whole circuit of neurons in this way, so I’m not sure how this could be done. Great question! To quote the authors of the paper on this one: “If indeed one cortical neuron is equivalent to a multilayered DNN, then what are the implications for the cortical microcircuit? Is that circuit merely a deeper classical DNN composed of simple ‘‘point neurons’’? A key difference between the classical DNN and a cortical circuit composed of deep neurons is that, in the latter case, synaptic plasticity can take place mainly in the synaptic (input) layer of the analogous DNN for a single cortical neuron, whereas the weights of its hidden layers are fixed (and dedicated to represent the I/O function of that single cortical neuron)”. 2. Dendritic spines and plasticity (e.g. STDP, BTSP) are definitely accounted for in many realistic network models. However, such simulations are done the “usual way”, by representing neurons with capacitors and resistors and adding plasticity-specific equations to synapses (e.g. increment the weight whenever the 2 neurons is a synaptic pair is co-activated. Or something like that). Since Beniaguev et al. simulated input-output transformations of a single neuron, I don’t think they modeled any plasticity (the neuron just responded to random inputs). When in the future people begin to make use of the DNNs to model networks of neurons, than synaptic plasticity will surely be accounted for (see the quote from above). 3. I’m aware of Michael Levin’s work, but haven’t looked at it in detail just yet ;) 
It’s true that bioelectricity is really important, not just in neurons, but also in regulating embryonic development, IIRC.

[@zacharyohare6029]

I'm ... NOT a scientist by profession or choice. But I AM fascinated by the digital/analog crossover... started with audio projects and a basic understanding of PWM... then realizing electricity/chemistry/physics/biology/neurology are merging at a level. This video to me was super helpful. It also has me contemplating how the paper mentioned essentially modeled a tiny brain microphone/recording booth, with digital playback and analog capture. It's like amplifier modeling. It's very very very difficult to capture all the possible inputs, but if you get enough of them, the capture and modeling is hard, but it can be sufficiently accurate to be useful, and then needs very little computational power after the model has been created. It's super intriguing and makes me wonder what would happen plugging the analog input/outputs of the dendrite/some would look like plotted as audio signals into some sort of modeler. Probably worse, more translation and compression happening etc. The fact that the neuron basically is a combination of an analog and digital signal is amazing to me. It does pulse width, essentially square wave when the specific voltage activates the dendrite spikes, and then duration and magnitude, and possibly- time-- I'm no interested in if there is a sort of standard "period" for each input/output. It was mentioned there are some differences, but is there a universal cap on what that is? Does a specific input change the effective period of responses? IE, would stress shorten the periods thus the perception of things happening faster? What is our internal "clock" speed. We know it isn't fixed at a top level, but on an individual cell, is it set? Are there a few that are defined based on the chemistry at work, and depending on the channels/ions/resistance etc? So we have individual inputs for location, a comparator for location which acts almost as an input it seems, that is part of a summed input of what order/how long. Then on each input we have duration and magnitude (x/y) and additionally, on dendrites themselves we have the NMDA acting as an additional square wave input? What about the periods of that input? Would different specific voltage inputs result in a response that is different consistently in period? Hey guys- I HATE school. But I might have to go back to school lol

[@evennot]

There's one more important property - temporal sensitivity. I did my diploma in hardware spiking neural nets (on a state-of-the-art Xilinx programmable chip) and this realisation was a wow moment. Basically, any digital system has a clock speed limitation. Natural neurons have much slower propagation speed, but activation is dependant on constant balance of race conditions + no two signals are coming at the exact same moment + basic quantum effects act as a gate (if one ion membrane changes its state from a pulse, concurring pulse sources will be denied and "rerouted"/lost). In the process of digital learning, resolution for these race conditions quickly becomes insufficient, signals are starting to clash, when they are coming in a single clock step. Biological systems, on the other hand, have physical time resolution, which is effectively infinite. No GHz clock can compete with this biological mechanics (only ASIC non-clockable implementation can utiliize this process). BTW, these effects manifest themselves with some neurotoxins: when receptors of a particular kind slow down, the whole system can be knocked out, or become very unstable

[@odettali1000]

thanks for the addition, would you have any papers explaining these basic quantum effects and the way they act as a gate?

[@evennot]

​@@odettali1000 I meant really basic discrete/quantized effects: such as in "Voltage-gated ion channels". Basically, you can't strip more electrons than the molecule has available for ionization. And you can't stick additional electron into non-ionized molecule. This electron will be "diverted" to go somewhere else

[@richtigmann1]

This is so interesting! I love how it combines and compares neuroscience and computer science. The production quality is so high

[@whitealpha2265]

Your videos are incredibly well made and are always a special joy to watch. Thank you for your high quality content, please keep it up :)

[@ArtemKirsanov]

Thank you!

[@CoachSamGlenn]

Spatial and temporal summation allows for LTP and LTD in order to control the plasticity of the neural network. That’s why you need NMDAR which are voltage gated dependent on AMPAR (the non linear system). As a neuroscience undergrad, I love your videos 🎉

[@Nobody-Nowhere-Nothing]

@Shimmy Shai u r gay

[@nixedgaming]

This channel is so incredibly underrated. Fantastic stuff. Really great.

[@naimneman4216]

that was a really great video! I was engaged every second of it, please keep uploading these topics!

[@celadon2048]

Amazing. Biology really is incredible in its exploration of forms.

[@fburton8]

As someone who teaches a bit of neuroscience at university level, I thought this video was superb from a didactic point of view and contained a lot of interesting content. You covered the basics of electrical excitability and action potentials in a compact way but also very clearly. I was prepared to wince at sodium ions "flooding" in but you used the less misleading word "rushes". Students tend to be led into erroneously thinking that the ion concentrations change massively during an AP when this isn't the case (especially for large axons like the squid giant axon). Anyway, I really like your style and content and have clicked Like and Subscribe.

[@vaheakli4551]

Great! Thank you, now I have a good enough video material to throw it in people who are lacking understanding biology moment. :) Especially for giving context of working of neurons nicely in one place. Some fancy neuroglia will not fit in this, but it's already great. I learned biology in school as well to understand, but not as well to explain something for others 🥰

[@os2171]

No doubt. You have created the best KZbin channel. Top quality in every regard. Cheers!

[@AffectiveApe]

Once again, stellar communication and animation work!

[@NoNTr1v1aL]

Absolutely brilliant video!

[@keyyyla]

Your animations are crazy. Keep up the great work!

[@gytoser801]

has reduced function and resulting in summing inputs because of leaky gates -Amplify voltage -Backpropogation : adjusts weights of input? NMDA gates (Neurotransmitter + adequate depolarization) (adjusts synapse connection) Dendritic Calcium Action Potential predictiion and logical results

[@PedramNG]

Useful stuff, I'm gonna relate some of these concepts to my paper that I'm writing. 😁 Thank you, beautiful video.

[@sabriath]

Well, it's kind of obvious if you just think about it for 2 seconds. Our "perceptron" is actually a single timed event which is more closely resembling the synapse to dendrite communication, using a master propagation chain as an offset, and the soma is another "perceptron" that details the chain into the axon....but everything is a timed sequence (as noted by the pulses, since channels need to recharge). All of this can be simulated using 2 layers across many "phases" (a phase is a deterioration of a signal as it fades across the channels, giving you the semblance of timing). When you have completed that, then you can realize that new neurons actually train themselves against already existing neuron clusters in order to output similar signals in order to get "the answer" faster in time, allowing the replacement of the slower one (this is how your memory changes slightly as you get older, possibly even losing the memory altogether). Each section of the brain has a different "job" to do, and when you solve that, you create the singularity....which is actually pretty easy. Don't worry, mine doesn't want to kill humans or anything.

[@FA18_Driver]

Amazing. Best channel on neural networks on YT by FAR!

[@willyouwright]

Great video. Now we can encode neural nets using a few new novel signal processing nodes !! Should make neural nets much faster and less power hungry..

[@abraarahmed1744]

I would definitely love to learn neuroscience in entirety by you. Thanks for the info. Always was fascinated by the workings of the brain but found it tought to wrap my brain around it, no pun intended. But your explanations make it clear and gives me a visual representation of the workings that i need. Thanks brother♥️ Looking forward for more.

[@Calvinizo]

I just found this channel out, and watched a few video's fully and I'm absolutely hooked and subbed directly, keep it up man! - The way you explain it is very easy to understand, even for outsiders!

[@qcard76]

It’s interesting to see a more mathematician-centric POV of how neurons are like neural networks, when from a neurobiologist’s perspective, it’s already obvious that real brain cells individually and collectively are already immensely powerful in a computational sense. So much so, it’s weird to see it phrased in this video that it’s the neuronal cells being “exonerated” relative to computational neural networks, when in reality it should be the other way around.

[@marz.6102]

The visual are hypnotizing of nerves and all that stuff A good choice for subscribing!!!!

[@adrianmoisa2281]

What the hell is wrong with the YT algo??? This video is amazing! It should have minimum 200k views ... This is a slap in the face of all nerds dedicated to STEM fields... Great work YT promoting great twrking videos! Great work!

[@ArtemKirsanov]

Thank you so much!

[@ahmedhadwan9273]

WAAAAAAAAAAAAAH- Your channel is literally top notch!! Thank s a lot for the content!

[@Hacktheplanet_]

What a great subject you have chosen to work on!

[@gileneusz]

bro, those explanations are so cool. I will definitely watch more of your yt videos. Just curious, where are you located?

[@SirFreddyPL]

Great video as usual! Could you explain the neural backpropagation in a future video? Is it similar to the backprop in artificial neural networks? Or maybe to the Forward-Forward algorithm for adjusting weights proposed recently by Hinton?

[@doppelrutsch9540]

I think the correct answer is "we don't know". If you figure out how actual neurons learn on a large scale you are a hot candidate for a Nobel Prize.

[@laurenpinschannels]

a quote I remember from somewhere is that if you can think of two ways neurons could be doing things, the brain is using both and a third or more that you didn't think of. though of course that only works for things that are biologically possible.

[@laurenpinschannels]

one point of interest is that you can approximate gradient backprop with predictive coding, and forward-forward doesn't seem to preclude predictive coding.

[@absta1995]

Neurons change weights or strength via long-term potentiation LTP and long-term depression LTD

[@jumpstar9000]

@@doppelrutsch9540 one thing is for sure, they don't do a bunch of global tensor matrix multiplication to do back prop, haha

[@lostammo9026]

The computer can’t think it will run in circles in what it’s programmed to do the human mind can break out of 100 of emotions

[@denis7325]

It's funny how the XOR gate is called the only "nonlinear" gate here because of non linear separability, while it is the only binary gate (among the usual ones) that is linear from an algebraic perspective (seeing bits as a vector space over F2). We can even use this to prove that with only XOR and NOT, you cannot build a circuit computing AND: XOR and NOT can only build linear functions, but AND is not linear.

[@shahinkh590]

divide the subjects into separate videos, you can upload more videos which will promote your content more often. and shorter videos will get more views. keep up the great work

[@pyromen321]

I have to say, I’ve never heard someone call XOR “kzore”, but I really like it.

[@davidhand9721]

I was having a hard time understanding how a neuron could be phase sensitive from your video on theta rhythm, but the "xor" neuron kinda makes that make sense. How narrow can the window of sensitivity be?

[@sadrien]

arbitrarily so.

[@nutzeeer]

Wow so not only the connections of the cells but proteins themselves assist in the process. Great!

[@egor.okhterov]

What is there in the neurons that's distinct from ANNs that allows them to do: 1. One shot learning (no need for backpropagation on GPU cluster with billions of examples). 2. No catastrophic forgetting. We don't forget old information after learning new knowledge. Old and new knowledge are incorporated together and complement each other. New knowledge doesn't override old knowledge. 3. Transfer learning. We can transfer skills and knowledge from one domain to another domain. If you could play CSGO then you will also be able to play Fortnite. 4.Planning/Self goal setting. ANN cannot choose and set a goal for itself - it's just a function that computes some value (or transforms one value into another). There's nothing in the deep neural network that does planning, it doesn't enumerate possibilities while computing something, it doesn't allocate time for a certain computation and doesn't do self-stop of that computation if it becomes too long. ANN is not self-reflective and there it cannot observe itself doing the computation. How to bridge the gap between what we have now with ANNs to have all of the 4 properties that we observe in the brains? It feels like that the architecture of ANNs is wrong on the fundamental level and there is no way to bridge the gap by simply increasing the number of layers in the ANN. Yes, even Transformer architecture feels like a step in the wrong direction and I don't see how it will be able to bridge the gap.

[@gpt-jcommentbot4759]

For no. 2 i think catastrophic forgetting is inevitable when the network is learning with backpropogation. If the network can automatically encode information into its memory it could possibly solve catastrophic forgetting if it is wired to not forget previous information.

[@avashurov]

Even with the current achievements in AI this year we still have a long way to go to approximate our own neurons. Artificial networks a still build pretty linearly with information propagating instantly in one direction. Not to mention that they are still have to be pretrained for a long period of time. Real neurons on the other hand can be connected in loops of diverse lengths. Their signals can arrive in any order. They include complicated timing mechanisms and can learn as they go.

[@ranbenayoun1978]

Amazing! learned about the XOR nural function for the first time, very intersting

[@aidenhastings6341]

This is so cool! I am becoming very interested in artificial neural networks and I always thought that the initial “simplified” model of the neuron was more or less correct

[@dragenn]

Amazing you broke it down so simple for someone like me to undestand. I love this channel!!

[@artem945]

Great video, Artem Not so long ago I found an overly increasing interest in machine learning and neuroscience and I love finding such great channels. Keep up the good work )

[@ArtemKirsanov]

Thank you! :)

[@SeviersKain]

The key function of these wonderful neurons is to store the whole process when we start to perceive things !!!

[@RomaineRC]

You're so good, man! Been trying to find a vid like this for a while

[@y337]

For part two, if you don’t know about this already (you might) please consider these organic neural networks here made from synthesized neurons: kzbin.info/www/bejne/bGjVaJl6h6efhMUsi=kSKjB9lhrXVbvxOS I found it extremely fascinating that they took donated foreskin cells, stem cell engineered them into neurons, and taught it to play pong similarly to a neural network, but not with back propagating, rather by bombarding its receptors with chaotic signals when it got scored on, and predictable (reward) signals when it scored, thus implying that neurons “goal” is to minimize chaos. Those guys claim they actually created sentience also

[@mitski3612]

I'm using my neurons to learn about neurons

[@vivekmarathe7733]

😅😅😅❤

[@jeanmahe8657]

Indeed my friend... me too

[@TabPGE]

Top Comment😂

[@Shy_guy9795]

Офигенные анимации!!! Невероятная визуализация, очень помогает понять. Где делали?

[@ArtemKirsanov]

Спасибо! Базовые анимации в Adobe After Effects, а активность нейронов - связка NEURON (для просчета самих симуляций) + Python + Blender

[@AryaPhoenix]

Funniest story, I am about to wrap up 2 weeks of lectures with Matthew Larkum here at the BCCN in Berlin, and the moment he started speaking about his theories and work on the role of dendrites I immediately remembered about this excellent video!

[@ufozxcv]

Thank you.this is the exact information i've been looking for so long.

[@scoopynoodle8418]

Great video! Love the effort you put into the graphics. Keep it up!

[@mohammadmedykhalilzadeh1263]

This video touched my soul. Now i know what im going to do for the rest of my life

[@willd1mindmind639]

Neurons are not electrical circuits because cells, no matter what type, whether that of elecrical eels or mice, are based on molecular biology not electricity. It is the movement of molecules within cells that can generate an electrical discharge, but it is the molecules that contain all the key information for activating cellular functions. All cells operate on this basic principle and neurons operate on molecules as the raw data of the network, not simply electrical charges. Not only that, but neurons can change shape over time, due to replication and reproduction while electrical circuits on a microchip cannot. And neural cells are able to handle a wide range of molecular values as "types" whereas electrical circuits only have 2 (on/off). And ultimately deep neural networks are software while neurons are physical organs. Fundamentally the fact that you need to retrain your model any time you want it to learn new things shows the stark difference between neurons and software neural networks. The brain is a recursive collection of networks from high to low level, with the implicit biological basis of those networks meaning that information is being actively "digested" and stored by the brain in its tissue via molecules. And a single neuron being a network of dendrite cells is a reflection of that. Unfortunately no such thing exists in computer science hardware or software.

[@olivercharles2930]

YET

[@petpaltea]

Great stuff, keep these videos coming!

[@nikkihuang7635]

So glad to have discovered your channel, thank you for this brilliant and beautifully made video! Any thoughts on connections between what you've talked about and valence encoding by neurons?

[@StratosFair]

Amazing video Artem, synthetic and clear explanations with impressive animations. As someone doing research on Deep Learning, I got super inspired by this video and I look forward to the future of our field !

[@ArtemKirsanov]

Thank you!

[@qtxrs-st7xe]

has reduced function and resulting in summing inputs because of leaky gates -Amplify voltage -Backpropogation : adjusts weights of input? NMDA gates (Neurotransmitter + adequate depolarization) (adjusts synapse connection) Voltage selectivity(originating between synapses), Voltage amplification, complications from being connected and depolarization affecting plasticity Dendritic Calcium Action Potential predictiion and logical results

[@rianpretorius8004]

Dude, this is brilliant! Nice! Definitely subscribed.

[@reinerheiner1148]

I must say I am very impressed with your content and how you represent it. May I ask what software you use for your animations? I want to start a youtube channel myself, also with more abstract information, although in another field. I think those animations would greatly benefit my viewers. So any pointers would be greatly appreciated.

[@ArtemKirsanov]

Thank you! I use mostly Adobe After Effects in combination with Python (matplotlib / manim modules) for creating mathematical animations. In this video, for 3D scenes with neurons I used Blender and a custom-written Python script to run a biophysical simulation in the NEURON software and bring the morphology and animation data into Blender

[@yonadabjaredguzmanmendoza1576]

Your channel is awesome, it's purely gold !! and not only for neuroscientist also for everyone. Thanks for sharing all of your knowledge with that easily and great animations. Cheers from Mexico :)

[@pyromen321]

Super interesting stuff. I’ve noticed that it’s common to have clusters of small CNNs within common neural network structures. In some way, that’s simulating this structure we see in neurons

[@StayCHilL24]

I've always been frustrated with the NN conversation being dominated with the idea of mimicing the human brain woth non of the nuance of the differences between the two. This really helped me understand the neuro science side of everything!

[@bjornrie]

I always find it annoying when people say "neural networks work just like the human brain". I mean, in a certain context it's not so wrong, but then you could say that everything that resembles a network(which you can find in many many natural and also social processes) works like the human brain. In the end the organization of the brain as a macro-structure is very different from neural networks. The brain is funtionally differenciated. The information processing in the brain is distributed into tons of complex autonomous sub-systems, of which each fulfills a specific function for the brain as a whole. While the brain can also re-organize itself within this macro-structure. This is the reason the brain can react so dynamically to it's environment and to disturbances/malfunctions. Modern society is organized as well after this principle of functional differenciation, for very similar reasons. But as far as I know every attempt to organize neural networks after this principle failed, at least doing it on such a high level the brain or society does.

[@tomaspecl1082]

This is so fascinating! Thank you for your awesome videos.

[@ArtemKirsanov]

Thanks!

[@tedarcher9120]

Also biological neurons can be steered by other neurons changing their activity completely.

[@justanokapi]

multilayered multilayeredness

[@zhangalex734]

I have a question: to the extent where the single neuron can perform XOR operations, can't it be argued that it is simply checking two thresholds instead of one? With both the lower bound and upper bound known it doesn't necessarily need to be multi-layer

[@ArtemKirsanov]

Well, technically yes, but to perform this check of the two thresholds you'll need at least 2 layers, if we are talking about conventional perceptrons, so in that sense it's multilayered (in this terminology "multi"=2 :D )

[@justanokapi]

thats is a second layer

[@zhangalex734]

@@ArtemKirsanov Ahh makes sense! Tysm!

[@claytonharting9899]

This game is such a good idea, it’s fun to watch

[@rumplstiltztinkerstein]

It is amazing how much more there is to improve about neural networks. Once we succeed at developing artificial neurons that are just as effective as biological neurons, we can go even further. Start developing neurons and neural networks that are even more advanced than biological ones.

[@proveritate1205]

I think this is true to a great extent, that the collective functioning neurons is broadly analogous to a digital deep neural network; but it's extremely likely that there's also a myriad of other fine-tuned characteristics and properties that a make the brain something more than a mere deep neural network, which truly confer its unmatched capabilities of problem-solving and integration.

[@thetransferaccount4586]

this was just the video I was looking for

[@alaaali7534]

mind blowing stuff going on here , the complexity of these biological neural systems is immense , adding there ability to adapt to new stimuli and changing "wieghts" adds alot more to there computational potential and learning capabilities . making me think that non bio neural systems will always be limited by their physical structure rendering them lagging behind the human brain thank you for the great video

[@olivercharles2930]

I still think non-bio neural systems could more or less replicate this complexity, but that is just my humble opinion.

[@alaaali7534]

@@olivercharles2930 well ، this will occur at some point but it will time for sure

[@olivercharles2930]

@@alaaali7534 Agreed on that.

[@pichirisu]

behavioral neuroscience is truly the most redundant pursuit of mankind

[@diadetediotedio6918]

Why?

[@goid314]

Very interesting video! Was pleasure to listen to and to watch

[@cinemaipswich4636]

No matter what the spin doctors say, we still do not have Artificial. Even Chat GPT is nothing but a glorified search engine. It may partially mimic a human, but within a few minutes, we find it cannot pass the Turing test.

[@kaushikkvasan5607]

Thank you for giving the references.

[@mickelodiansurname9578]

I think Artem, you were talking for 30 seconds,when I went looking for the subscribe button.

[@DrApocalyptus]

Love your channel dude

[@potisseslikitap7605]

Awesome video thank you for that!

[@tommyhuffman7499]

You're video is absolutely amazing!!!

[@ArtemKirsanov]

Thank you!

[@robfielding8566]

the summed inputs just happen to be the same as a "cosine similarity comparator", which is the same as a dot product. that could be implemented in a totally non-biological system with pipes of water of varying pipe width. indeed, somebody has 3D printed an artificial neural net to calculate the MNIST data set with light as the input and output (ie: shine in a transparency with hand-written digits, and one of ten outputs is the brightest one that is the recognized digit). That is a neural net using no electricity, or moving parts; but it can't learn weights online. the real mystery is the mechanism that changes weights. that's what the "it's not back-propagation" and "it's forward-forward" debates are about. (in_1 w_1 + in_2 w_2 + ... + in_n w_n) = dot(in, w) = cos( angleBetween(in,w) ) Almost nothing about artificial neural networks seem to be biologically plausible; including the layers. I suspect that what we are discovering is: - while it's important to understand how the brain actually works; it may not be important at all to implement it in the same way (ie: chemically) - learning seems to be about constantly predicting your inputs, and weights changing to reduce prediction error. ie: next video frame prediction will require a 3D model of what is in the video frames - after your black box is catching up and making correct sensory input predictions; that all worked because the blackbox (function approximator) is creating layers that GENERALIZE well. To Generalize means that.... all sensory input you get could be stored like a sort of database; but all input from eyes and ears are slightly different.... but representations should cause unseen inputs to be predicted well. right now, complicated and layered representations seem to be essential for the function approximation to settle on a useful state. - it's not backprop, but maybe it's forward-forward; where a compelling notion of what sleep is will arise.

[@rhysknight8681]

Unreasonably great channel

[@moormanjean5636]

Pleaseee make a video on "Context-sensitive neocortical neurons transform the effectiveness and efficiency of neural information processing"

[@yoverale]

18:51 does it imply that a more accurate model of how neurons work would be actually a base 3 or ternary numeral system? It’s not 1 or 0, but 0, 1, 2 states equivalent to under current threshold, over current threshold, over saturation threshold 🧠

[@agranero6]

That is why i prefer the term "unit" for ANN instead of neuron.