Microsoft Research
AI deep learning expert and University of Montreal Professor Yoshua Bengio talks about deep learning—what it is, how it got there, where it’s going, and how you can learn more about it. He discusses the latest in neural nets, unsupervised learning, generative adversarial networks, soft attention, optimization, and more.
See more on this video at https://www.microsoft.com/en-us/research/event/faculty-summit-2017/
Source
Damn right you're privileged! I Assume you are anyway.
I believe that to say a child learns about gravity, liquids and so on without supervision is to take a narrow view of what constitutes supervision. The child's body, and the environment in which it lives, provides extremely rich "supervision" in the sense that, for example, a child who cannot manage basic operations involving gravity cannot move around much. A child who does not have some grasp of how liquids behave will not get a lot of juice from a cup — most of it will be spilled. Thus questions in the nature of "Am I doing this right?" or "what can I do with this object" are actually answered in the strongest possible terms by the child's body and his/her environment — which incidentally are not separate at that age and arguably in some sense cannot ever be disentangled from the point of view of the brain.
an unseasoned ear hears scary premises being tossed around like lunch milk from one of the causal tendrils of the SKYNET event singularity which is yet to happen.
Bengio is so cool
not simplifying or rounding of fractions opens infinite fractions. 1/3 .
that moment when kids try to control their parents…
The lure of Neural Networks / Deep Re-inforcement Learning lies in its ability to OPTIMIZE. While Humans have many admirable features (and some less so), they are absolutely NOT OPTIMAL in their current environment. DNNs will be more effective and efficient . Two questions: 1) Before AI becomes AGI, what does the LOGICAL, inevitable end-game (ooops, punny) look like?
2) Once a DNN crosses the thin line between rich environmental awareness and thin (animalistic) self-awareness, it will be unstoppable, just like any powerful wild animal.
Humans cannot define 'consciousness', yet an improved, faster, optimized version is being sculpted, without any apparent concern over control: Utter Hubris; Humans have been 'in charge' on Earth for some time through INTELLIGENCE alone, and now the Replacement is proudly being engineered by Idiot Savants. There is NO FAILSAFE on INTELLIGENCE, natural or artificial. The higher Intelligence will ultimately rule.
why you keep touching Bengio hand ?
I downloaded this shit.
gained a lot from this
could help me about my equation How extract higher level features from stack auto encoder i need simple explain
I need to understand how input 30 and output 28 in stack auto – encoder
Watch The Wangtta Experiment
https://youtu.be/XIffUH05cJY
Great interview, thank you to you both.
Learned a lot