What a luxury to be able to watch this on-demand, from anywhere, and for free!
@kentrader24894 жыл бұрын
This was a great presentation
@ElevateTechCA4 жыл бұрын
Glad you enjoyed it!
@atifadib4 жыл бұрын
Man he has a great sense of humour
@kuldeepsingh876 Жыл бұрын
and has the clarity at the same time.
@mangoldm Жыл бұрын
Are hidden Markov models as relevant as Ray Kurzweil suggested?
@Tothefutureand Жыл бұрын
13:13 this photo of rnn is most best photo I’ve ever seen about rnns
@klausunscharferelation6805 Жыл бұрын
about the singularity As Ray Kurzweil says When the whole universe becomes a computer, What does it calculate? Even though the purpose for calculating has already disappeared?
@vtrandal3 жыл бұрын
At 8:59 some comments about RIM. What is RIM?
@bcbcbcbcbc Жыл бұрын
Research in motion, the original name for Blackberry who used to make smart phones.
@shivakumarcd6 жыл бұрын
"so if you're obsessed with only being one correct answer and you're being able to prove you get it, backpropagation is not for you nor is LIFE"
@loopuleasa6 жыл бұрын
classic Geoffrey
@wishall0076 жыл бұрын
He hasn't lost the British sarcasm
@shubhampandey1997shreeg4 жыл бұрын
Actually by that line prof Hinton refers to the time when no one believed in his line and work of research and that decade taught him a great deal of patience until the technology reached a certain level to cope up with his knowledge.
@shivscd3 жыл бұрын
@Ernest Alonzo WOW.. Do you think people who watch these video fall for you?
@RyckmanApps Жыл бұрын
That was the best of his one-liners and zingers.
@dripcode2600 Жыл бұрын
Always been fascinated with computer neural networks. Exciting times!
@neerajsingh-xf3rp Жыл бұрын
deeply insightful
@kuldeepsingh876 Жыл бұрын
Geoffrey Hinton sir has the super clarity about his thoughts. I love it. He does not beat around the bush.
@madamedellaporte4214 Жыл бұрын
He should be put through court for paying with the future of humanity. Of us all so he can make a big stash of money and we see our children have no future ..That is what happens with mad scientists who let their vanity take hold of them.
@PaulScotti3 жыл бұрын
Could someone clarify? He explained that backprop is better than "mutation" because backprop is parallelized vs. serialized -- but his explanation doesnt convey why backprop is achievable in parallel?
@brendawilliams8062 Жыл бұрын
Maybe if you have a neg. and a positive direction then you’d be best covering the known ground. I don’t know either.
@panda5088 Жыл бұрын
Because of the way the vector math works, you can calculate the difference in the result that a change to any one weight or bias would cause. Therefore you can adjust the result by manipulating multiple weights or biases at the same time. Here's a pretty good video explaining back prop more in-depth: kzbin.info/www/bejne/f53KZJp9mtyEa7c
@xiaochengjin64785 жыл бұрын
watching such an amazing video at 5 am
@Alp091115 жыл бұрын
loved this, thank you!
@ElevateTechCA4 жыл бұрын
No, thank YOU for checking us out!
@bensonmwaura94946 жыл бұрын
A tensor for paradigm shifts.
@mohammedalmukhtar54285 жыл бұрын
He is a Genius..Period.
@holmerlike83953 жыл бұрын
AND, you must be a complete moron for believing such ! Or perhaps simply, just riding the gravy train... Keep it go'in Buddy !
@j.wilmararcila4150 Жыл бұрын
Gracias doc, que LINDO Mundo en El que sumerced SE mueve !
@Gabcikovo Жыл бұрын
11:27 Tomáš Mikolov just smiled :))
@Gabcikovo Жыл бұрын
17:16 :D
@Gabcikovo Жыл бұрын
17:18 🤣🤣🤣
@Gabcikovo Жыл бұрын
🤖🥇🤣🐬
@Gabcikovo Жыл бұрын
19:23 word2vec
@Gabcikovo Жыл бұрын
20:51
@caonima3236 жыл бұрын
what is the time of this speech ?
@ElevateTechCA6 жыл бұрын
This speech took place in September 13, 2017 at Elevate TechFest.
@jj-ry8xv6 жыл бұрын
1998
@caonima3236 жыл бұрын
ethan chow you e d
@nguyenngocly14844 жыл бұрын
You can make inside-out neural networks with fixed weighted sums (dot products) and adjustable (parametric) activation functions. Rather than the other way around. Then you are free to use high speed fast transforms for the fixed dot products.
@powertester5596 Жыл бұрын
This is extraordinary!
@paulmitchell53495 жыл бұрын
Knowledge is accessible data.Intelligence is ability to infer.
@Bmens715 жыл бұрын
paul mitchell like this quote
@TheCriticsAreRaving5 жыл бұрын
17:16 Hinton flips off the audience
@TheHamoodz6 жыл бұрын
How can someone be intelligent enough to invent neural networks and entertaining enough to give a presentation like that. Its almost unfair lol.
@ArtOfTheProblem5 жыл бұрын
and you forgot how clearly he explained the 'key concepts' there is maybe 300 pages of a typical book on the subject compressed into about 20 phrases in this talk.
@shubhamp.41555 жыл бұрын
He did not invent neural networks
@prashanthadepu30134 жыл бұрын
@@shubhamp.4155 but he brought to life many of them and redesigned completly
@mateuszanuszewski694 жыл бұрын
It is just math, and nothing else. So if one understands math at academic level can easly learn how neural networks will work and how to manipulate notations on them to get different types. And i am not talking about "oh learn Neural networks in 5 minutes" and people show you how to program a model in tensorflow.
@dearheart2 Жыл бұрын
RNN is fun. I made a RNN for translation (word in, "thoughts" (RNN) works out), over the breaks in 1 week in high school in early 80ties. It could learn new words, structures and did an ok translation. Just made it for fun, like all the NN, AI at that time.
@Gabcikovo Жыл бұрын
9:37 💜
@Gabcikovo Жыл бұрын
9:47 :D
@Sp8e Жыл бұрын
I like this guy.
@HerrWortel4 жыл бұрын
Hinton is giving us the finger at 17:15 xD
@paulmitchell53495 жыл бұрын
Learning is not necessarily intelligence.More rapid learning means to twig the concept and apply the concept to new problems.
@cowardmildredj.72504 жыл бұрын
loved this, thank you!
@dearheart2 Жыл бұрын
Used evolutionary algorithm for training NN's in the 80ties. Worked well already then. Limited hardware, had to program all myself, but I got general AI that could be used for almost anything.
@rkara26 жыл бұрын
Process or singularity is the Heart of AI. Alan Turing clearly define this in his 1936 paper on computable numbers. Input > Process > Output (Turing complete expression or circular) Process (Turing incomplete expression or non-circular) !DA
@dannyiskandar6 жыл бұрын
amazing ..thank you
@Free_Ya_Mind Жыл бұрын
In the nutshell, Artificial Neural Network is just a parametric composite function trained using the chain rule of derivative.
@jmf3210 Жыл бұрын
Cool it with the 1960's slide presentation....definitely needs a producer..
@janaenae1338 Жыл бұрын
I really love you!!!❤
@loopuleasa Жыл бұрын
this guy was waaaay ahead of his time he casually defined what a thought is, and this thought never left my head 5 years ago
@samdavisok Жыл бұрын
25:00
@zakali925 жыл бұрын
Absolutely fascinating for a dummy like me
@nbme-answers5 жыл бұрын
14:47 symbols go in, symbols go out but in the middle it can't be "symbols"!
@fallhdesls52264 жыл бұрын
smart!long life
@bingeltube6 жыл бұрын
Recommendable
@obsiyoutube48285 жыл бұрын
smart!long life
@damoonrobatian93713 жыл бұрын
Geoff himself doesn't even know how it works! It just works!!! What kind of scientist could be satisfied with this type of "reasoning"? HYPE
@bopeng95046 жыл бұрын
Great job Geoff. Pray that God would bless your life!
@mateuszanuszewski694 жыл бұрын
omg so many ads
@morthim4 жыл бұрын
if you are going to call people stupid you shouldn't contradict yourself and agree with the people you insult.
@u2naru Жыл бұрын
This guy now says that AI is dangerous after decades of leading projects on AI. Why now not the time this presentation was done?
@yadayada111986786 Жыл бұрын
He ays himself he was surprised by the pace of the AI development. He thought these dangers would come much later and slower
@ancestralrocha77095 жыл бұрын
Some basic shit? Did I hear correctly?
@leo.budimir5 жыл бұрын
Damn, he looks like Palpatine here
@abcdxx10595 жыл бұрын
lol yeah
@mutterich52903 жыл бұрын
LM21 was geht ab
@dr.mikeybee6 жыл бұрын
Professor Hinton is amazing, but there are too many of these NN for dummies lectures. They're starting to clog the space. It's a shame he didn't say anything really interesting here.
@mtoman6 жыл бұрын
True, finding advanced talks is getting pretty hard.
@pd.dataframe28335 жыл бұрын
For advanced knowledge you dont come to youtube....you fucking read research papers
@atomskreigns80715 жыл бұрын
Sivaram Karanam and even that's not true you can search any ML topic on KZbin and get a lecture as advanced as u like a whole series of them
@SameenIslam5 жыл бұрын
Did you not read the title of this video? Clearly says foundations
@OptionGal4 жыл бұрын
@@pd.dataframe2833, not entirely true. Some of the best research papers are published and presented at symposiums such as this one. We are all very lucky that there are videos of these podium presentations so that we may also be inspired to learn.
@janaenae1338 Жыл бұрын
❤️🧡💛💚💙💜💙💚💛🧡❤️🧡💛 We are ALL the SAME PERSON experiencing life in a BUNCH OF DIFFERENT BODIES!!! which means that EVERY PERSON that you meet, is really just YOU... LIVING IN ANOTHER BODY!! you see..you are INTERACTING with YOURSELF at ALL TIMES!!! & once you understand this,you can achieve unity! I and my father are one Love Thy Neighbor as Thyself 💜💙💚💛🧡❤️🧡💛💚💙💜💙💚
@robertolupot2497 Жыл бұрын
Interesting. So how does the death of one body affect the living body?
@TomerBenDavid4 жыл бұрын
Wow :)
@zzbeasley6 жыл бұрын
Is a thought more than an image? Think about it.
@JazzyGinger110 ай бұрын
Hello🦩🦩🦩, God the Father loves you so much that He sent Holy, Sinless Jesus (His Holy Son) to earth to be born of a virgin. Then He grew up and died on a cross for our sins. He was in the tomb for 3 days, then Father God raised Holy and Sinless Jesus Christ (Y'shua) to life! He appeared to people and went back to Heaven. We must receive Sinless Jesus sincerely to be God's child. John 1:12 says, "But as many as received him, to them gave he power to become the sons of God, even to them that believe on his name." Will you receive Christ sincerely?
@bobtarmac1828 Жыл бұрын
Today, Losing your job to ai agents is unacceptable. Ai Jobloss is here. So are Ai as weapons. Can we please find a way to Cease Ai / GPT? Or begin Pausing Ai before it’s too late?
@sakathvenu5 жыл бұрын
@AnwarAdnan-e5wАй бұрын
And now Dr Hinton resign from google to alert people about the dangerous of AI. this remind me with Oppenheimer
@m3n4cE6 Жыл бұрын
look at them, fatal wound/mark on their forehead
@yvespetit2 жыл бұрын
A spiteful professor who thinks his tinkering with computers does good for humanity! Talk about speech recognition, the machine voice announcing a caller on our phone system is always wrong.