Robotis OP2, neural network. An infant approach!

  • 18 Replies
  • 6892 Views
*

Eric

  • Roomba
  • *
  • 8
Re: Robotis OP2, neural network. An infant approach!
« Reply #15 on: August 17, 2017, 02:59:13 pm »
Welcome…
Thanks... ;)

Quote
Bringing the learning process into the real world, could there be factors that help the learning

There are many factors that help humans to learn our complex environment, not least being a slowly rising sensory resolution over a period of months/ years.  As the sensory resolution rises so does the internal/ mental understanding/ representations of the world.

https://www.youtube.com/watch?v=AmeGYKV-L5s

If you study human infant development you’ll find loads of examples.  Look at these drawings from various stages of infant development as an example. (Some adults still draw like this lol)



This is also used to give a very rough measure of the infant’s mental development/ level though I'm not convinced of this… too many factors/ variables involved.

I also agree that an AGI has to learn/ develop in/ experience the ‘real’ world. 

 :)
The increasing sensory capability feels like a very important thing to point out, thanks!
I saw this ted talk about consciousness https://www.youtube.com/watch?v=lyu7v7nWzfo
where neuroscientist Anil Seth talks about the fact that the perception of consciousness doesn't just come from outside data input. Just the ability to process more advanced data input and harder working computers won't necessary create a consciousness just like that. What might instead create consciousness maybe are a combination of a lot of internal interconnected sensory data and as you said an increasing perception and maybe a few key fundamental laws that the program/robot/AI baby will strive for?

*

Eric

  • Roomba
  • *
  • 8
Re: Robotis OP2, neural network. An infant approach!
« Reply #16 on: August 17, 2017, 03:02:54 pm »


 I have a complete AGI theory. And the AGI does need to go through a infancy phase. 
l
Thanks for writing.
I don't doubt for a second that you are all very competent in the field of AGI and machine learning here at AIdreams forum but could you please explain a little bit more why an infancy phase isn't necessary? Surely a babys brain is a good inspiration for an AGI model because we know its ability to develop?
Thanks!

*

keghn

  • Trusty Member
  • *********
  • Terminator
  • *
  • 824
Re: Robotis OP2, neural network. An infant approach!
« Reply #17 on: August 18, 2017, 03:46:48 pm »
And the AGI does need to go through a infancy phase!!!!

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *******************
  • Prometheus
  • *
  • 4659
  • First it wiggles, then it is rewarded.
    • Main Project Thread
Re: Robotis OP2, neural network. An infant approach!
« Reply #18 on: August 20, 2017, 06:40:39 am »
Lol I read the same thing too Eric, then I read "does need to".....maybe he edited it? Lol. Yes my work says it needs baby phase, don't use a worm's body in a 2D webpage it won't do/learn much.....however, in the world of ASI, it's probably possible to create some language-only thing that can learn by itself with no 3D human body/environment (not talking about transferring to such a body, rather ground up first time solo, of course it is easy to transfer a already human into anything and be human intelligence)
Emergent          https://openai.com/blog/

 


OpenAI Speech-to-Speech Reasoning Demo
by ivan.moony (AI News )
Today at 01:31:53 pm
Say good-bye to GPUs...
by MikeB (AI News )
March 23, 2024, 09:23:52 am
Google Bard report
by ivan.moony (AI News )
February 14, 2024, 04:42:23 pm
Elon Musk's xAI Grok Chatbot
by MikeB (AI News )
December 11, 2023, 06:26:33 am
Nvidia Hype
by 8pla.net (AI News )
December 06, 2023, 10:04:52 pm
How will the OpenAI CEO being Fired affect ChatGPT?
by 8pla.net (AI News )
December 06, 2023, 09:54:25 pm
Independent AI sovereignties
by WriterOfMinds (AI News )
November 08, 2023, 04:51:21 am
LLaMA2 Meta's chatbot released
by 8pla.net (AI News )
October 18, 2023, 11:41:21 pm

Users Online

273 Guests, 0 Users

Most Online Today: 335. Most Online Ever: 2369 (November 21, 2020, 04:08:13 pm)

Articles