Thanks to our sponsor, Bright Data: Train your AI models with high-volume, high-quality web data through reliable pipelines, ready-to-use datasets, and scraping APIs. Learn more at brdta.com/aisearch Viewers who enjoyed this video also tend to like the following: You Don't Understand AI Until You Watch THIS kzfaq.info/get/bejne/Z8d9ZK6K29KYdKs.html These 5 AI Discoveries will Change the World Forever kzfaq.info/get/bejne/nN-GncRemp2peac.html The Insane Race for AI Humanoid Robots kzfaq.info/get/bejne/b5aEgL1jy9edd6c.html These new AI's can create & edit life kzfaq.info/get/bejne/abGPf6R41NTXgIk.html

Seems to me like a lot of people compare the "learning" a human does during it's lifetime to the training process of a LLM. I think that it would make more sense to compare the training process of a neural network to the evolution process of the human being, and the "learning" a human does during its lifetime to in-context learning in a LLM.

How do human brain actually work? It feels like all the research out there are still incomplete

I built a custom spiking neural network for resolving a last-mile logistics efficiency problem. I agree with your assessment: Very efficient. Complex logic.

The opening statement is so true. As a student of this field, I think that this is not said enough and anyone not well versed in machine learning just does not get how bad the current situation is.

Absolutely would love that video about the Neuromorphic Chips!!

Just waited for somebody to point the tremendous energy problems of current AI. Thank you

8:33 not only is this "human brain" computer more efficient, but I heard the first stages of creating a new instance is pretty fun, can't confirm, never done it, but they say it is

The human brain developed over a time span of millions of years. How much energy did that process use?

1. It's funny that we are trying to create something (AGI) that replicates something else that we do not understand (the human brain). 2. Any neural network that truly emulates the human brain won't need to be trained in the sense you discuss. It would just be. It would learn and be trained by it's design. It would start training immediately and continue to train throughout it's existence. I don't see us ever creating something like this anytime soon (see statement #1).

First and foremost, I am a biologist, but I have quite an extensive background in computer science as well. I have some fundamental concerns with the efforts to develop AI, and the methodologies being used. For these models to have anything like intelligence, they need to be adaptable, and they need memory. Some temporal understanding of the world. These efforts with LNN strike me as attempting to re-invent the wheel. Our brains are not just a little better at these tasks than the models. They are exponentially better. My cats come pre-assembled with far superior identification, and decision-making systems. Nevertheless, that flexibility and adaptability require an almost innumerable set of 'alignment' layers to regulate behavior, and control impulses. To make a system flexible, and self-referential is to necessarily make it unpredictable. Sometimes the cat bites you. Sometimes you end up with a serial killer.

Definetly make a video on neuromorphic chips And i think the other neural networks outside the scope of this video should have their seperate video as well

Spiking neural networks and any future neural networks, sounds like where agi and asi are actually at.

Thanks!

HOLD ON A SECOND!!! did you think we wouldnt notice???☠☠ 3:52

i wrote a spiking neural network from scratch, it can learn but it's not as efficient as learning as typical nn as you can't do gradient descent effectivey, instead you need to adjust the neurons based on a reward. now you can backtrace and reward the last neurons and synapses that resulted to the output you want but it is limited, it works better when you don't just reward the lasts, but reward according to the desired output, still, pretty cool to run and it makes nice visualizations.

We currently simulate neural networks programmatically, which is why they are so inefficient. The problem is, people are so impatient for AGI that they have concentrated all their efforts on achieving it rather than developing an actual neural network.

Glad to hear this. Back in 2010 I was looking for an alternative to network graph system still in use today. Basically we have a scaled version of a decades old tech that we now have the horsepower to run. I will say current neural matrices are but a partial model of a brain. I studied a portion of grey matter neural matrices see the book Spikes. "Fred Rieke, David Warland, Rob de Ruyter van Steveninck, William Bialek". The human brain is exponentially more complex than any scaled multi million GPU, TPU, CPU system. Good video.

8:40 "Human brain only uses 175kWh in a year" - Since human brain cannot work without the body you have to treat [brain+body] as one entity (which is ~4 times more), unless it's a brain in a jar.. but yea i guess still very efficient.

Thanks for the video 😁. I really enjoyed it! I'm also very interested in those neuromorphic chips you talked about in the end.

Really nice recap. I've subscribed. Keep it up.

this is my first video from your channel, and I am already impressed!

Awesome content, as always. I would love to know more about neuromorphic chips. Thanks.

Thank you for your very interesting talk. I have a question. Does this entire system run on the same cycle (clock)? Or does each node run on its own timing?

I think it is important to highlight that current artificial neural networks are not based on how human brains work but inspired by biological neural networks. Human brains are really complex thanks to half a billion years of evolution of the brain. There is a pretty good book that serves as a primer on neuroscience called “A Brief History of Intelligence”. If you enjoyed Sapiens you will love this book.

Oh good - was wondering if spiking and liquid NNs were similar. Both trying to emulate our current understanding of human neurons....neat!

I don’t get how the Liquid NN should continue to learn if you only train the output layers once and the Reservoir stays the same as well (according to you the reservoir gets randomly initialized before training and from there never changes, just allows for information to circle/ripple in it)

This comment is to let you know that you should, in fact, make a video on neuromorphic chips.

Yes please - I'd love to see you do a video on neuromorphic chips! Keep up the good work!

In response to you question at approx 28 minutes: Yes, I would like to see more on Spiking Neural Networks!

5:18 I agreed with everything until this point. Gemini did prove that models can learn post training. As they did learning a new language

Great educational video, thanks.

Super useful video, thank you!

Not being able to self-improve is the single greatest limitation of LLMs.

and YES- i would love to learn from You about the neuromorphic chips :)

A very competent compression of complex ideas - well done mate!

Great video, thanks. How data resulting from training is stored and accessed. I am familiar with SQL databases and would like to know what happens when, say, a picture of a dog, is submitted to some AI for identification. Thanks

@theAIsearch can you please share the source from where you get these information

《 Arrays of nanodiodes promise full conservation of energy》 A simple rectifier crystal can, iust short of a replicatable long term demonstration of a powerful prototype, almost certainly filter the random thermal motion of electrons or discrete positiive charged voids called holes so the electric current flowing in one direction predominates. At low system voltage a filtrate of one polarity predominates only a little but there is always usable electrical power derived from the source Johnson Nyquest thermal electrical noise. This net electrical filtrate can be aggregated in a group of separate diodes in consistent alignment parallel creating widely scalable electrical power. As the polarity filtered electrical energy is exported, the amount of thermal energy in the group of diodes decreases. This group cooling will draw heat in from the surrounding ambient heat at a rate depending on the filtering rate and thermal resistance between the group and ambient gas, liquid, or solid warmer than absolute zero. There is a lot of ambient heat on our planet, more in equatorial dry desert summer days and less in polar desert winter nights. Refrigeration by the principle that energy is conserved should produce electricity instead of consuming it. Focusing on explaining the electronic behavior of one composition of simple diode, a near flawless crystal of silicon is modified by implanting a small amount of phosphorus on one side from a ohmic contact end to a junction where the additive is suddenly and completely changed to boron with minimal disturbance of the crystal pattern. The crystal then continues to another ohmic contact. A region of high electrical resistance forms at the junction in this type of diode when the phosphorous near the ĵunction donates electrons that are free to move elsewhere while leaving phosphorus ions held in the crystal while the boron donates a hole which is similalarly free to move. The two types of mobile charges mutually clear each other away near the junction leaving little electrical conductivity. An equlibrium width of this region is settled between the phosphorus, boron, electrons, and holes. Thermal noise is beyond steady state equlibrium. Thermal transients where mobile electrons move from the phosphorus added side to the boron added side ride transient extra conductivity so they are filtered into the external circuit. Electrons are units of electric current. They lose their thermal energy of motion and gain electromotive force, another name for voltage, as they transition between the junction and the array electrical tap. Aloha

A neural network is just probability function which gives how likely the occurrence is, so for a given input how much probability of getting the following output. A output with high probability is the most likely answer to your input. And the network just help to calculate that probability by nodes networks biases, back propagation, residual network, matrix, calculus etc, it seems maths, computer and physics coming together in one place

Good simple explanation of the current state of neural nets and where they’re going.

Neuromorphic chips are a topic I would like to see a video on. seems like there is a lot of potential here.

if spiking neural networks gets implemented then what will be the future of existing neural networks and the infrastructure and the heavy duty hardware that's required for traditional neural networks AI apps, what is your opinion on this topic

Great video, thank you for your work!

But what will hapen if you combine a normal neuron network with a liquid neuron network? So that these two networks can cooperate with each other in certain situations. Like one being used for new information or similar patterns and the other one for specific rules or how to react in specific situations.

So the readout layer of liquid NN is basically perceptron? Coz in your image it's just one layer of data and no explanation on how the readout layer is trained.

Fantastic chanell! Super nice!👏👏👏🗣💯💯🔥‼️‼️‼️‼️‼️‼️❤

You earned a subscriber rom Kenya....kudos

yes, it is the plasticity and learning ability that neural networks lack, thank you for these ideas.

Thank you for your hard work.

Hinton has suggested a way to implement feed forward training, as the brain appears to. Can you update this for us, please?

Yes please. Let’s learn about neuromorphic chips!

What’s the difference between LNNs and tradition NNs with online learning?

Very interesting to hear about these emerging architectures.

Firstly, thank you for producing such an informative video. One thing I would like to add is to say that current neural networks require a lot more training data than say a three year old child in order to preform a simple classification from such as distinguishing cats from dogs. Our current models require tens of thousands of examples in order to be properly trained. Where as a three year old child would require perhaps five or six examples of each. I would propose an architecture which I am calling Predictive Neural Networks where neurons are arranged in layers where neurons predict which other neurons will fire depending on the input data. For example, high level neurons may be trained to detect an eye but should also 'know' where to find the next eye or where to find the nose. Because a cats nose looks different from a dogs nose and is one of the main distinguishing features, it should be possible to train these networks with much fewer examples.

These liquid neural networks sounds like the liquid state machines i used in my masters. Whats the differences between LNNs and LSMs

Very informative and well put together video, thanks!

Awesome video! I would love that video on neuromorphic chips!

Like Intel alluded to regarding their neuromorphic chip, we can use AI to fix the library issue. So neuromorphic is close. Maybe just 3 years out. Liquid neural networks might need a bit more help from AI to solve the kinks, but I think AI is the key here as well in order to have the technology ready to be launched.

Silly question: Why not use (some) all of them in combination, with a superodinate network (perhaps the liquid one) that either learns or is told by training which method to deploy for which type of data? The idea, once again, is to mimic the brain, with modular information processing at lower levels but the executive function at a higher level.

Very well explained

when will we get neural network chips in our phones? I want a layer of capacitors on my transistors

great informative video! Thanks a lot Please make us a deep dive into neuromorphic hardware.

Amazing presentation, thank you! I would love for your to do a follow-up on the potential of neuro-morphic architectures.

This is very interesting! The reservoir layer seems like the digital analog to the subconscious mind! I really love your explanation of this new type of neural network.

Super nice and educational video 👏🏻👏🏻👏🏻👏🏻👏🏻

How are these variants of neural networks being viewed by companies like OpenAI?

So awesome. Thanks! Neuromorphic, please :)

Would the liquid reservoir perhaps be a ferrofluid in a well of some kind with transducers around it? Trying to picture the engineering implementation of it. Or am I taking this too literally? It seems there would be a minimum spatial wavelength of any physical liquid, thus limiting the physical miniaturization. Very cool video, thank you for your efforts!

will Liquid neural network be able to work on cpu? 😢😅

Does anyone know of the company Brainchip - they say their models can learn?

Hi, I would like to know more about the spiking neural networks, their types, limitations, challenges, performance, online learning capabilities, etc. Thanks!

Yes neuomorphic chips video please

Nice explanation. Thanks.

Make video on chips yes

"we just need more nodes" that's what they think

From dots and lines of curves, from CPU to Brain links and related objects with movements in space with timed calculated of predictions of possibilities in interest or hobbies

I had no idea before this video that other regenerative AI are coming along & already supersede traditional probagation considerably in many use cases. It gives me hope that an AGI breakout is much closer than they say.

The age of analogue computing is coming. Great video for sure.

👍 for neuromorphic chips

excelente resumo para entender as dificudades de software e de hardware para a construção dessas redes "liquidas". obrigado

would it not be best to combine all these? a standardized base set of a nueral network interface with fluid like restructuring to generate patterns and spike detection to recognize it´s own patterns over time. something that would truely mimic a brain in all senses taking the drawbacks away by combining and maintaining all the benefits.

I think time for analogue computers to shine

So does this mean we could not get AGI on a traditional neural network? Or would it just depend how large the data set is?

When it comes to technology, if it's technically possible and there's economic demand for it, it will happen. Given the stupendous amount of energy needed to train current models, the incentives to perfect these more efficient models will lead to rapid progress. There's no way things stay this inefficient for too long.

Excellent video.

YES WOULD LIKE A DIAGRAM OF DIGITAL LOGIC MODEL, OR ANALOGY DEVICES CONFIGURED, OR THE MICRO CIRCUITS CURRENT FOR THE DIFFERENT CLASSES OF NEURO LOGIC IMPLEMENTATIONS IN RESEARCH AND COMMERICAL APPLICATIONS AND HOW ONE IS TESTED AS DIGITAL LEVELS OR WAVEFORM OUTPUTS

Liquid neural networks + SNN

That’s a smart rock damn

Is this about Apple Intelligence or about Machine Intelligence in general? 😉 Can (actual) neurons also loose potential (slowly over time) if it doesn't receive spikes for some time?

Neuromorphic chips are a good subject for a new video soon.

Thank you so much for this information video. It was great to learn what is happening and research in AI. At the current rate, do you think we could see AGI robots in the coming years?

I think compression is underrated

Liquid neural nets are an interesting application of analog computing (contrasting with discrete math/logic used by traditional neural nets). Analog computers have been making a comeback in general. I wonder if analog computer hardware of some kind could be used to run them.

I used a CNN combined with a Liquid Time-constant Network (which is part of LNNs) for my university dissertation, which seems pretty powerful itself, I was able to train a robot to follow me based on image input given the same trained environment and clothes as in the training data. It's interesting stuff

I’d argue neural networks can improve with the use of further trading and/or different training data which can change or reconfigure under utilised weights to improve overall accuracy.

Feels like there would be a tipping point with a liquid model where it starts out by just working, and then is tasked with making a better model based on its learned measurement of its own current performance. Given it can change and adapt, it could improve on its own design and rince/repeat.

Some nuance to be made: models are updated from time to time even if they don't get a new name or version. So GPT4 designates a series of training. About energy, the processors are getting better at energy consumption, so applying a linear factor to the number of weights is a huge overestimation.

Well, how long would it take for a human brain to learn everything gpt knows- probably hundreds or thousands of years

Is there anyone studying AI who can answer a fundamental question I've been wondering: What is the relationship between inference and overfitting as the size of a model goes to infinity? I recently saw that the overfitting issues come and go as the model size increases. Seems to not converge on overfitting in the limit sense as the model size gets larger.