He is a pure genius that has immense deep knowledge. I was amazed how he explained that our brains work based on building analogies and that "rational thinking" develops later in life. It's freaky to imagine that this field is exponentially growing and the outcome and the application potential of neuronal networks would be limitless and I hope that they would not be used for malignant motives. Many thanks for posting this great interview.
Thanks for uploading this in depth talk on ANN. Professor Geoffrey is undoubtedly at the forefront of science, the advances he and his team (including students) establish will expand the knowledge and understanding of science and thus man.
It felt like a sizeable portion of this interview went like this: Interviewer: Dystopian fiction scares me, could you please make me less scared? Expert: Well, instead of talking about fiction, here's what's going on in the real world. Rinse & repeat.
amazing talk ...very insightful that we are not rational people but deriving our decisions from our unconscious mind or rather what he called vectors of feature representation that is more like an analogy based reasoning than logical reasoning. Very deep about how our brain works!
but it goes deeper, beyond the 0100101010101 brain to.. 5D ah cant work with 5D bad luck no easy answers. learning is earnt. even dying doesnt stop us ill be coming straight back.. this place works perfectly.
computer technology is able to create a new language that can be understood by the human brain, animal brain and computer machine at once. machine learning technology can definitely do it, for example; what happens to synapses, aukson and dendrites when canadians learn Japanese or vice versa. The language coding of the brain can later be used for further technology.
What if the brain is virtual, just bits of data. What then ? the language coding is happening in a database outside the "tesseract" you're living in Please tell me how you convince god to let you get data ? with 100% precision, not.. when it suits the system for the system is in a fight with entropy. Signal to noise. Data.. information This is not information. Never was. This is a STANDARD called ENGLISH. Those are just words. Pretty hard to be ambiguous, yet.. we each MAKE OUR OWN INFORMATION and store it outside this reality. This is easily logically explained to any non-coward human.. Machine with senses under the same constraints would tell you "this universe.. is not real" just like Einstein did.. SOMETHING IS MISSING. Consciousness.. they knew.. Wigner specifically quoted, if we have the right quotes... says exactly what you need to hear.. But oh right.. people said NO DONT BOTHER doing those experiments, WE KNOW how those will turn out They turn out the OPPOSITE to what they predict, EVERY TIME But no, lets not be that type of experimentally verifiable scientist. Gosh what a terrible thing that would be ABSOLUTE BULL SHIT Virtual reality, you, me. Prove me wrong you win all the money and fame in the world. THE MATERIALIST IS DEAD. EXTINCT. DEAL WITH IT Or science progresses the worst possible way. With each death of an old scientist we get 1 in some huge number closer. No thankyou I have OTHERS magnificent specialist work.. and i have generalist on lock.. for now. THIS IS SO EASY. AMA. ANYTHING AT ALL.
so Damn Interesting, ...I'm glad you mentioned the solution of applying a parallel network for an understanding of the initial networks results. This is a Life and Death race to the Future, and what concerns me the most is what happens when we not only dont understand why the results are presented but we deliberately do not implement those results, what will that do to the AI's
Make them even worse than they are now.. because people think they can just think Like Brian Greene says at 1337 in Lex Fridman 232 The notion that if you put this inanimate things together just right suddenly you get "aware" consciousness thing.. ITS INSANE ! damn right sir. He's the one to tell us its all a simulation. Its so damn obvious. One day, when we're collectively ready.
he is asking "for a mate" the goldfish masses who think Terminator from the future is gonna kill their distant future some shit i would ask but what if.. i asked already if brain virtual.. then what does the neural net get used for to verify simulation with ML model that has senses and tries to work the world out WITHOUT human bias of "nah dont test that it HAS to be physical you have to alter it to measure" proven wrong over and over and over and just more "hmm if we tweak the math" no. just no. youre all WRONG its a simulation end of story memory, not here, out there experience databases out there senses, data streams (AV plus 3x touch, 2 are biological touch and analyse, one is tactile) and the rest is easiest thing ever except for stuck in materialist or coward Brian Greene THE MASTER ! on #232 of LEX FRIDMAN ! GO Go there bring up 13:37 (really?) Exactly what he said. To say theres no chance I'm right is to be laughed at forever in the future, once comprehensively white flag dead materialism DEAD Particle physics becomes a subset, which explains the variables in the very complex smart equations out there. It's definitely not stupid enough to model little o's going weeeeeee lets make conscious=yes in a brainnnnnnnnnnnn we know how to code we use MONGO DB ! yay weeeeeeeeeeeeeeee yay us weeeeeeeeeeeeeeeeeeeeeeeee IM IN BOYS THIS WAY ! IM A PARTICLE NOW YAYYYYYYYYYYYY
PS 0 and 1.. 1 thing.. PRIMORDIAL conscious.. boring. Two things.. BORING 0 1 1 0 and 1 1 1 1 etc. bored. but billions of animals on primal NPC ? now you are talking.. stable ? in we go.. full immersion 0 chance to detect fakeness... smash open the planet enough times wasting energy you hit the wall. Planck laughs and tips hat.
Saying how cats are females and dogs masculine is actually tautology in Serbian language. FYI, we have genders for every single noun and surprisingly enough, cat (noun) is feminine, while dog is - masculine.
Hm, why people ask about autonomous cars, is stupid, because we have them already. Maybe not in mass production, and not as good as people, but they are and they are not so bad.
A neural network in nature doesn't imply "intelligence" at least not human intelligence. It only implies a specialized collection of cells designed to accomplish a specific task. The key here is that these are specialized cells and not a one size fits all generic algorithm. Neural Networks in computer science are a general purpose algorithm but their value only comes as a result of specialized frameworks and code around them that makes sense of the results. And they are computationally very expensive because they are not specialized to a specific task. So the statistical results that they produce have no meaning and have no "value" outside of very custom code and logic built into the system. Now compare that to neural networks in nature. They are much more sophisticated and produce more accurate result based on years of evolution around a specific task. All nerves deal with sensory data and as a function of this, they all have some inherent behaviors common across the board. These common "building blocks" are what become advanced "cognitive" abilities based on evolution as in the human species. One of these common building blocks is the ability to say one set of sensory data is "similar" to another, just like in math where you have similar triangles. Therefore auditory nerves can tell at a very fundamental level that one sound is "similar" to another or even "the same". Similarly on a very basic level optical nerves are able to tell if one set of optical data is "similar" to or "the same" as another. It doesn't matter what the optical data is or how it is "labeled" , because that labeling is the function of another set of specialized cells. And right now current neural networks are not built around that same kind of computational building block. This is why humans and animals can recognize things after one or two times seeing it, while neural networks take a very long time. But the only reason for that is because the current state of Neural Nets does not take advantage of the most important aspect of Neural Nets and that is feature extraction. If you give a single image to a neural network, it should be able to generate hundreds if not thousands of "features" based on very simple concepts like "color value" (rgb) or shape. And then on top of that you build up more complex features like parts and whole, (meaning something is part of something else), then from there you build up more complex feature sets on top of that, all from pure visual input and not any sort of labeling. Evolving a neural network to be come "specialized" at seeing then would be much more powerful, especially when combined with larger and faster memory by which you could run functions on to compare against the next image being processed. This has nothing to do with naming objects. Dogs and cats can see just fine and different species of animals see better than humans, but they cant talk and they don't "think" like we do. However, we know they "recognize" things when they see them. Language and labeling would be a function of another specialized set of neural networks, working in conjunction with the first, but specialized in other things. A good example of specialized "optical" Neural Networks would be something like the new AI tool called Sensei.
hm semi interested only if you can explain what cells do anything like frontal lobe, pineal gland (DMT dream, DMT near death experiences) for people like the dude who has almost 100 iq, 90ish.. maths job or something.. family... finds out one day sir you have no brain wow rude no look.. black xray .... some born this way.... detected at birth........ are now infected with "down syndrome x 100" idk something.. anyone where you detected ACTUALIZED it at or before birth is now effectively brainless, well done medical technology the one who didnt get detected is happy, normal.. noone NOONE KNEW until he was adult and whatever it is that happened happened cant find this story then you are bad at googling.. its about questioning our understanding of consciousness YET again 5D is where the memory is. he can remember things with almost ZERO BRAIN MATTER fun fact a farmer once cut a chickens head off it lived for months. TINY bit but didnt cut its head right off. it had some brain stem he fed it with an eyedropper because he was so amazed he had to.. then i suppose he was like :( serious.. kinda emotionally attached now.. course it died it was in a coma.
neural networks and children see dogs more as males and cats more as females because cats have features that are more similar to women and dogs have features that are more similar to men like big and strong and aggressive
7:38 but then you get English captions from English that instead of saying something normal.. say something completely stupid CANT FIND IT im only human but I said LOL WOODEN !!!!! can't be more than a couple of weeks of big data mess, oops my bad :/
G. Hinton might be considered a marketing "Genius". He successfully rebranded the decades old field called multi-layered neural networks,... simply by applying the word "DEEP"
Google Are Definitely NOT! Making proper tools available to public, Public Version Of Tensor-Flow is no where near the same as Google's internal use version.
Thanks for uploading this in depth talk on ANN. Professor Geoffrey is undoubtedly at the forefront of science, the advances he and his team (including students) establish will expand the knowledge and understanding of science and thus man.
Well i have some rather huge doubts because i was hoping he would say.. well neural nets won.. but it is only an approximation, and is very limited sigh
![[Full] 4 ต่อ 4 Celebrity EP.910 | 22 ก.ย. 67 | one31](http://i.ytimg.com/vi/4TR3MVpOiw8/mqdefault.jpg)
This man is a national treasure and a virtual god. His portrait should be on our Canadian currency post haste.
Geoffrey Hinton is British!
Claiming he is Canadian... is specious at best
@@1984-x3w He's british yes but he lives in canada so we'll allow the canadians to claim him
i realize Im kind of randomly asking but do anybody know a good place to stream newly released tv shows online?
Gotta love Geoffrey Hinton since his insight into applications of neural nets is wonderful and always so well articulated.
My impression from him is that neural nets are just a side show, he wants to decode the brain.
@@TheReferrer72 agreed
He is a pure genius that has immense deep knowledge. I was amazed how he explained that our brains work based on building analogies and that "rational thinking" develops later in life. It's freaky to imagine that this field is exponentially growing and the outcome and the application potential of neuronal networks would be limitless and I hope that they would not be used for malignant motives. Many thanks for posting this great interview.
Very good talk. Apart from his knowledge of neural networks the man is apparently also highly skilled in circumventing political correctness issues.
i think i've watched every talk from geoffrey hinton now, i need more!
Thanks for uploading this in depth talk on ANN. Professor Geoffrey is undoubtedly at the forefront of science, the advances he and his team (including students) establish will expand the knowledge and understanding of science and thus man.
It felt like a sizeable portion of this interview went like this:
Interviewer: Dystopian fiction scares me, could you please make me less scared?
Expert: Well, instead of talking about fiction, here's what's going on in the real world.
Rinse & repeat.
Gotta colllect a clickbait answewer
amazing talk ...very insightful that we are not rational people but deriving our decisions from our unconscious mind or rather what he called vectors of feature representation that is more like an analogy based reasoning than logical reasoning. Very deep about how our brain works!
but it goes deeper, beyond the 0100101010101 brain to.. 5D
ah cant work with 5D bad luck
no easy answers. learning is earnt. even dying doesnt stop us
ill be coming straight back.. this place works perfectly.
computer technology is able to create a new language that can be understood by the human brain, animal brain and computer machine at once. machine learning technology can definitely do it, for example; what happens to synapses, aukson and dendrites when canadians learn Japanese or vice versa. The language coding of the brain can later be used for further technology.
What if the brain is virtual, just bits of data. What then ? the language coding is happening in a database outside the "tesseract" you're living in
Please tell me how you convince god to let you get data ? with 100% precision, not.. when it suits the system for the system is in a fight with entropy. Signal to noise. Data.. information
This is not information. Never was. This is a STANDARD called ENGLISH. Those are just words. Pretty hard to be ambiguous, yet.. we each MAKE OUR OWN INFORMATION and store it outside this reality. This is easily logically explained to any non-coward human..
Machine with senses under the same constraints would tell you "this universe.. is not real" just like Einstein did.. SOMETHING IS MISSING. Consciousness.. they knew.. Wigner specifically quoted, if we have the right quotes... says exactly what you need to hear..
But oh right.. people said NO DONT BOTHER doing those experiments, WE KNOW how those will turn out
They turn out the OPPOSITE to what they predict, EVERY TIME
But no, lets not be that type of experimentally verifiable scientist. Gosh what a terrible thing that would be
ABSOLUTE
BULL
SHIT
Virtual reality, you, me. Prove me wrong you win all the money and fame in the world. THE MATERIALIST IS DEAD. EXTINCT. DEAL WITH IT
Or science progresses the worst possible way. With each death of an old scientist we get 1 in some huge number closer.
No thankyou
I have OTHERS magnificent specialist work.. and i have generalist on lock.. for now. THIS IS SO EASY. AMA. ANYTHING AT ALL.
so Damn Interesting, ...I'm glad you mentioned the solution of applying a parallel network for an understanding of the initial networks results. This is a Life and Death race to the Future, and what concerns me the most is what happens when we not only dont understand why the results are presented but we deliberately do not implement those results, what will that do to the AI's
Make them even worse than they are now.. because people think they can just think
Like Brian Greene says at 1337 in Lex Fridman 232
The notion that if you put this inanimate things together just right suddenly you get "aware" consciousness thing..
ITS INSANE ! damn right sir. He's the one to tell us its all a simulation. Its so damn obvious. One day, when we're collectively ready.
Anyone knows which Arxiv paper is he mentioning with 0.04 percent error rate?
at 30:35 btw
Great man
Thanks😁
Thank You Geoffrey Hinton
You should see my Videos, I have solved it and will have a AGI protoype shortly.
42:07 That's the reaction to that magnificent speech? People should bring a little bit smarter hosts in front of geniuses like Hinton.
totally agreed. these type of people have always used terms like "people wonder". In reality, this is completely their thoughts.
he is asking "for a mate"
the goldfish masses who think Terminator from the future is gonna kill their distant future some shit
i would ask but what if.. i asked already
if brain virtual.. then what does the neural net get used for
to verify simulation with ML model that has senses and tries to work the world out WITHOUT human bias of "nah dont test that it HAS to be physical you have to alter it to measure"
proven wrong over and over and over
and just more "hmm if we tweak the math"
no. just no. youre all WRONG its a simulation end of story
memory, not here, out there
experience databases out there
senses, data streams (AV plus 3x touch, 2 are biological touch and analyse, one is tactile)
and the rest is easiest thing ever except for stuck in materialist or coward
Brian Greene THE MASTER ! on #232 of LEX FRIDMAN ! GO
Go there bring up 13:37 (really?)
Exactly what he said. To say theres no chance I'm right is to be laughed at forever in the future, once comprehensively white flag dead materialism DEAD
Particle physics becomes a subset, which explains the variables in the very complex smart equations out there.
It's definitely not stupid enough to model little o's going weeeeeee lets make conscious=yes in a brainnnnnnnnnnnn we know how to code we use MONGO DB ! yay weeeeeeeeeeeeeeee yay us weeeeeeeeeeeeeeeeeeeeeeeee IM IN BOYS THIS WAY ! IM A PARTICLE NOW YAYYYYYYYYYYYY
PS
0 and 1.. 1 thing.. PRIMORDIAL conscious.. boring. Two things.. BORING 0 1 1 0 and 1 1 1 1 etc. bored.
but billions of animals on primal NPC ? now you are talking.. stable ?
in we go.. full immersion 0 chance to detect fakeness...
smash open the planet enough times wasting energy you hit the wall. Planck laughs and tips hat.
APEDATE 0
Commander reporting
POO !! we all throw poo
transmission ends.
APEDATE 1
Commander reporting
Light.. then dark.. very peculiar.
POO !! etc
transmission ends
Saying how cats are females and dogs masculine is actually tautology in Serbian language. FYI, we have genders for every single noun and surprisingly enough, cat (noun) is feminine, while dog is - masculine.
Hm, why people ask about autonomous cars, is stupid, because we have them already.
Maybe not in mass production, and not as good as people, but they are and they are not so bad.
Can someone give a link for paper on the so called 'press secretary network' which labels images by connecting up two networks
A neural network in nature doesn't imply "intelligence" at least not human intelligence. It only implies a specialized collection of cells designed to accomplish a specific task. The key here is that these are specialized cells and not a one size fits all generic algorithm. Neural Networks in computer science are a general purpose algorithm but their value only comes as a result of specialized frameworks and code around them that makes sense of the results. And they are computationally very expensive because they are not specialized to a specific task. So the statistical results that they produce have no meaning and have no "value" outside of very custom code and logic built into the system.
Now compare that to neural networks in nature. They are much more sophisticated and produce more accurate result based on years of evolution around a specific task. All nerves deal with sensory data and as a function of this, they all have some inherent behaviors common across the board. These common "building blocks" are what become advanced "cognitive" abilities based on evolution as in the human species. One of these common building blocks is the ability to say one set of sensory data is "similar" to another, just like in math where you have similar triangles. Therefore auditory nerves can tell at a very fundamental level that one sound is "similar" to another or even "the same". Similarly on a very basic level optical nerves are able to tell if one set of optical data is "similar" to or "the same" as another. It doesn't matter what the optical data is or how it is "labeled" , because that labeling is the function of another set of specialized cells. And right now current neural networks are not built around that same kind of computational building block. This is why humans and animals can recognize things after one or two times seeing it, while neural networks take a very long time.
But the only reason for that is because the current state of Neural Nets does not take advantage of the most important aspect of Neural Nets and that is feature extraction. If you give a single image to a neural network, it should be able to generate hundreds if not thousands of "features" based on very simple concepts like "color value" (rgb) or shape. And then on top of that you build up more complex features like parts and whole, (meaning something is part of something else), then from there you build up more complex feature sets on top of that, all from pure visual input and not any sort of labeling. Evolving a neural network to be come "specialized" at seeing then would be much more powerful, especially when combined with larger and faster memory by which you could run functions on to compare against the next image being processed.
This has nothing to do with naming objects. Dogs and cats can see just fine and different species of animals see better than humans, but they cant talk and they don't "think" like we do. However, we know they "recognize" things when they see them.
Language and labeling would be a function of another specialized set of neural networks, working in conjunction with the first, but specialized in other things.
A good example of specialized "optical" Neural Networks would be something like the new AI tool called Sensei.
hm semi interested
only if you can explain what cells do anything like frontal lobe, pineal gland (DMT dream, DMT near death experiences)
for people like the dude who has almost 100 iq, 90ish.. maths job or something.. family...
finds out one day
sir you have no brain
wow rude
no look.. black xray ....
some born this way.... detected at birth........
are now infected with "down syndrome x 100" idk something.. anyone where you detected ACTUALIZED it at or before birth
is now effectively brainless, well done medical technology
the one who didnt get detected is happy, normal.. noone NOONE KNEW until he was adult and whatever it is that happened happened
cant find this story then you are bad at googling.. its about questioning our understanding of consciousness
YET again
5D is where the memory is. he can remember things with almost ZERO BRAIN MATTER
fun fact a farmer once cut a chickens head off it lived for months. TINY bit but didnt cut its head right off. it had some brain stem
he fed it with an eyedropper because he was so amazed he had to.. then i suppose he was like :( serious.. kinda emotionally attached now.. course it died
it was in a coma.
I can't understand the cats and dogs male and female part.
neural networks and children see dogs more as males and cats more as females because cats have features that are more similar to women and dogs have features that are more similar to men like big and strong and aggressive
7:38 but then you get English captions from English that instead of saying something normal.. say something completely stupid
CANT FIND IT im only human but I said LOL WOODEN !!!!! can't be more than a couple of weeks of big data mess, oops my bad :/
36:35
the next einstein is this guy you will see
G. Hinton might be considered a marketing "Genius". He successfully rebranded the decades old field called multi-layered neural networks,...
simply by applying the word "DEEP"
Google Are Definitely NOT! Making proper tools available to public, Public Version Of Tensor-Flow is no where near the same as Google's internal use version.
superjaykramer can you be more specific?
Awesome video
Thanks for uploading this in depth talk on ANN. Professor Geoffrey is undoubtedly at the forefront of science, the advances he and his team (including students) establish will expand the knowledge and understanding of science and thus man.
Well i have some rather huge doubts
because i was hoping he would say.. well neural nets won.. but it is only an approximation, and is very limited
sigh
excellent presentation,, very informative,, especially the medical applications,, thanks very much.
well be telling great storys about how we were the first to know about this tech... and how we were the ones prepared to the changes it brought..