Recent Posts

Pages: [1] 2 3 ... 10
1
I am very into creating the AI code, and have lots of instructions for my employee. I am so into it that I push the greatest lengths to create such a real baby human body and get Blender right on par with UE4. Blender is indeed not just a modeling tool after all. It is giving me multiple advantages over UE4 too.

So, what are you planning on doing? Are you going to get a real robot, Darwin OP2?
2
Yes I am going to and will be able to put advanced AI in my simulated human baby, and interact with it in real-time. What specifically would you like to know?

Here you can watch one of my recorded videos showing it:

Impressive, it seems like you're more into the 3d modeling than developing the machine learning to simulate behaviour though.
Thanks for showing me and I wish you good luck in the future.
3
General Project Discussion / Re: Robotis OP2, neural network. An infant approach!
« Last post by LOCKSUIT on August 15, 2017, 09:25:32 pm »
Yes I am going to and will be able to put advanced AI in my simulated human baby, and interact with it in real-time. What specifically would you like to know?

Here you can watch one of my recorded videos showing it:
4
General Project Discussion / Re: Robotis OP2, neural network. An infant approach!
« Last post by Eric on August 15, 2017, 08:50:44 pm »
Thanks for your reply LOCKSUIT.
Hey there!

So you're looking at this robot: http://www.trossenrobotics.com/shared/images/PImages/Darwin_OP_1.jpg
Yes, that's what I was thinking. Any thoughts?

My suggestion is to go 3D simulation. Darwin cost 12K and my simulated realistic baby already has fingers and toes and a tongue! Infinite battery. Speed up simulation. And many many more big advantages.

I would teach you for free every rope to know, fast, to be able to pick up my software and start working.
That simulation thing sounds very interesting and impressive if you've managed to simulate a human being in it. Could you please tell me more and if there is a possibility to integrate machine learning in it.

I would love to see my experiments in real life and the developing behaviour of the robot and its neural network. I'm thinking that with the guidance of a real human it might show interesting results.
Thanks again!
5
General Project Discussion / Re: Robotis OP2, neural network. An infant approach!
« Last post by keghn on August 15, 2017, 08:49:16 pm »
 i like unsupervised learning.
 The CNN of lately are supervised detectors.
 Atari DQN are cool and are more in the direction of unsupervised learning and have little temporal memory going for them.

 For making a neural network AI you are going need a temporal memory recording of when the CNN activated. And where it is. GPS is
not really need.


6
General AI Discussion / Re: essay topic
« Last post by ivan.moony on August 15, 2017, 08:38:34 pm »
You don't have to bump up your tech and deal with humans. Just create AI, and it bumps itself up instantly and all the world and beyond will become heaven.

Great thinking :). I just hope that the first one will work for benefit of all beings, not just for one.
7
General Project Discussion / Re: Robotis OP2, neural network. An infant approach!
« Last post by keghn on August 15, 2017, 08:33:42 pm »

  404 solution?: 

      http://yann.lecun.com/exdb/mnist/index.html


8
General Project Discussion / Re: Robotis OP2, neural network. An infant approach!
« Last post by LOCKSUIT on August 15, 2017, 08:19:04 pm »
Hey there!

So you're looking at this robot: http://www.trossenrobotics.com/shared/images/PImages/Darwin_OP_1.jpg

My suggestion is to go 3D simulation. Darwin cost 12K and my simulated realistic baby already has fingers and toes and a tongue! Infinite battery. Speed up simulation. And many many more big advantages.

I would teach you for free every rope to know, fast, to be able to pick up my software and start working.
9
General AI Discussion / Re: essay topic
« Last post by Zero on August 15, 2017, 08:11:06 pm »
Why 90% computers are sold with windows?

There are a number of possible responses to this question. My favorite is that 90% of computer users are too stupid to run Linux, but it's simply not true. What is true is that the number of computers sold with Windows these days is vanishingly small compared to the billions and billions of computers that run Linux in the form of Android, and the alternative to Android on those computers is still not Windows, so the premise of your question is actually false.

Hey, good answer! Blurring the lines between smartphones and computers, that's clever!

My favorite answer: "Because 90% computers are sold with windows!"

EDIT:
Back to the topic, I think the game changer here is the concept of "app". There's a store, you click the button, you have it installed, end of story. Phones have it, Win10 has it, Ubuntu has it (sort of), Firefox, Chrome, ...etc. This is the exact point where new tech can breach through existing heavy-weights, and you see it everyday: success stories, on an app market, coming from nowhere. So I'm rather optimistic about this.
10
General Project Discussion / Robotis OP2, neural network. An infant approach!
« Last post by Eric on August 15, 2017, 07:50:16 pm »
Hello AI folks,
My name is Eric and I'm a student in Engineering physics in Lund, Sweden. I am very interested in machine learning and I've just started learning about how these things work. I’ve come to some realizations, so far I've understood that when you want to teach a coded program something either you have
1. A data set with input data and result which you run through your program to train it. For example the MNIST Data http://yann.lecun.com/exdb/mnist/base
2. You generate your own data and result by having a simulation environment. Just like the examples we've seen when a program learns how to play a video game.

After realising these two types of ways to train for example a neural network I started to wonder if you could do it differently. I started thinking about a couple of things.
1. Bringing the learning process into the real world, could there be factors that help the learning or would it just be, like in many other experiments, a too complex enviromen with too much data to handle for the learning program.
2. Could we compensate this environment with supervised learning? Could this affect the quality of the input data?

My idea:
Have a robot like the the Robotis OP2 http://en.robotis.com/index/product.php?cate_code=111310
as an agent acting in my home. The inputs will be all the sensoric data it can detect and all it’s movements in form of walking, falling, getting up and so on. As far as I’ve understood I would need something like a cost-function, giving it a rating of how well it has achieved.
I’m thinking of trying to model its neural network to get as close as possible to an infants mind, being entirely impulsdriven (like babies are in their early years). That would mean that it’s objective would change all the time and therefore also the costfunction(?) which would decide the weights of each neuron, right?

I understand this sounds like an extremely difficult task but do you have any inputs with your knowledge of how machine learning actually works?
I’m trying to aim for a more flexible but initially simple system that can modify itself to a greater extent.

Thanks for all the help!

Pages: [1] 2 3 ... 10

Users Online

21 Guests, 1 User
Users active in past 15 minutes:
ivan.moony
[Trusty Member]

Most Online Today: 31. Most Online Ever: 208 (August 27, 2008, 09:36:30 am)

Articles