Go Back   the Magicball Network > Forums > MBN Main Forums > Off topic

Welcome to the Magicball Network.

You are currently viewing our site as a guest which gives you limited access to view most discussions and access our other features. By joining our free community you will have access to post topics, communicate privately with other members (PM), respond to polls, upload content and access many other special features. Registration is fast, simple and absolutely free so please, join our community today!

If you have any problems with the registration process or your account login, please contact contact us.

Off topic General off-topic chat goes in here.

Reply
 
Thread Tools
  #1  
Old 2016-05-22, 18:30
Neko's Avatar
Neko Neko is offline
Neko
 
Join Date: Oct 2000
Posts: 8,619
deep neural network machine learning

anyone following http://www.wired.com/2016/05/google-alpha-go-ai/ the fact that computers now can beat the best humans in a game where they cannot compute all possible outcomes?

This deep neural network learning sounds really cool...
Reply With Quote
  #2  
Old 2016-05-22, 19:42
Neko's Avatar
Neko Neko is offline
Neko
 
Join Date: Oct 2000
Posts: 8,619
you can train it to play mario kart

Reply With Quote
  #3  
Old 2016-05-23, 00:44
Darkflame's Avatar
Darkflame Darkflame is offline
Classic
 
Join Date: Feb 2001
Location: Sol, Earth, NL
Posts: 22,496
Send a message via ICQ to Darkflame Send a message via AIM to Darkflame Send a message via MSN to Darkflame
I posted this on the tech thread, but it deserves its own.
Google open-sourced a lot of it.
One significant part of it is TensorFlow, which is how this stuff gets trained;
https://www.tensorflow.org/

(Currently used for both their speech and image recognition as well as a few other things)

When I say image recognition, incidentally, I mean "it can recognize objects in a image"

https://youtu.be/eve8DkkVdhI

https://www.raspberrypi.org/blog/ras...ion-google-io/

Oh, and you can technically use this right now yourself;
https://cloud.google.com/vision/

However, its not free. They will ask for your credit card information even for a demo. (which sort of makes sense - as I can imagine this is probably quite intensive work on the server side so they cant just give it away or make it advert based easily).
__________________
http://fanficmaker.com <-- Tells some truly terrible tales.
-
Phones & Tricorders & Blobs & Bombs & 3D Printers & TVIntros also;stuff

Last edited by Darkflame; 2016-05-23 at 00:50.
Reply With Quote
  #4  
Old 2016-05-23, 10:06
Neko's Avatar
Neko Neko is offline
Neko
 
Join Date: Oct 2000
Posts: 8,619
do you think we can use tensorflow to learn how to play games?

that would be teriffic
Reply With Quote
  #5  
Old 2016-05-23, 12:02
Darkflame's Avatar
Darkflame Darkflame is offline
Classic
 
Join Date: Feb 2001
Location: Sol, Earth, NL
Posts: 22,496
Send a message via ICQ to Darkflame Send a message via AIM to Darkflame Send a message via MSN to Darkflame
Maybe.
My understanding though is once you train a AI in this way its actually very hard to work out exactly how its working.
Remember those "deepdream" images that were popular a few months back?

http://deepdreamgenerator.com/

That was a incidental result of Google trying to figure out how its image recognition AIs were actually recognizing stuff.
Essentially they tried to run their AI backwards.
Attached Thumbnails
Click image for larger version

Name:	dream_69920984b7.jpg‎
Views:	244
Size:	216.0 KB
ID:	10041  
__________________
http://fanficmaker.com <-- Tells some truly terrible tales.
-
Phones & Tricorders & Blobs & Bombs & 3D Printers & TVIntros also;stuff
Reply With Quote
  #6  
Old 2016-05-23, 21:53
Neko's Avatar
Neko Neko is offline
Neko
 
Join Date: Oct 2000
Posts: 8,619
yes! that is kinda scary. It's just pure math you're looking at. You cannot see the 'code' as there is no 'code'.


I really want to learn this, but I don't want to just randomly start studying math without knowing what basics and subjects you need to study.

I know programming, but this is a really different world
Reply With Quote
  #7  
Old 2016-05-23, 22:50
Darkflame's Avatar
Darkflame Darkflame is offline
Classic
 
Join Date: Feb 2001
Location: Sol, Earth, NL
Posts: 22,496
Send a message via ICQ to Darkflame Send a message via AIM to Darkflame Send a message via MSN to Darkflame
It is fairly different. Nothings definitive anymore,the logic isn't absolute anymore.

However, from what I have seen glancing at the Tensorflow tutorials, its actually very flow-chart based (as in, literally a flow chart editor).
I think a "programmers mind" might be enough to get started, although thats just a guess as I havnt had time myself to look deeply.
__________________
http://fanficmaker.com <-- Tells some truly terrible tales.
-
Phones & Tricorders & Blobs & Bombs & 3D Printers & TVIntros also;stuff
Reply With Quote
  #8  
Old 2016-05-24, 14:39
Lupin's Avatar
Lupin Lupin is offline
Previously Link
 
Join Date: Dec 2001
Location: Strasbourg, France
Posts: 2,705
I've been looking into deep learning for a while now, and I think I have a good grasp of the general picture.
The best resource I found so far is this online book: http://neuralnetworksanddeeplearning.com/
There's definitely a bit of math there, but it's quite manageable.

I also find the TensorFlow playground useful to help visualize what's actually happening.

TensorFlow is actually not bringing much new stuff to the table, it's main value is in providing a framework that works both for production and research, while most other older frameworks are research-oriented. It's also got better tooling. But the important stuff is in the math, not in the particular framework you use.

There are 2 important things to grasp in my experience to get a good grasp of the whole picture.
The first is the idea of Machine Learning in general and particularly the role of the "optimization/cost function" in learning.
The second is to get a good intuition for neural networks (both biological and artificial ones). NNs are not new stuff, even Deep Neural Networks, and they are a quite straight-forward model of what's inside our actual brains.

The field is quite complex, definitely not something you can learn overnight. But it's moving very very fast, and I'm pretty sure we're facing a revolution of the same magnitude as personal computing or the internet.

Particularly, the last developments from DeepMind (Atari games, AlphaGo) are a very significant step towards artificial general intelligence (AGI).
Self-driving cars, the Falcon 9 landings, as well as many huge tech successes of the recent years all gravitate around similar ideas and techniques.
The DeepMind paper about Atari games is mind-blowing, even if you don't go through the math in details.

Heavy progress seem to be made when there's a cross-pollination of ideas between state of the art neuroscience and comp-sci. We're in for an interesting decade.
Reply With Quote
  #9  
Old 2016-05-25, 01:09
Polaris's Avatar
Polaris Polaris is offline
Polly parrot
 
Join Date: Jan 2007
Location: Tippett Island
Posts: 5,671
Wow that's impressive stuff...
I don't have much to say other than please keep talking about this '
__________________
<((((((((((((([[[========================]]])))))))))))))>
Reply With Quote
  #10  
Old 2016-05-25, 17:16
Neko's Avatar
Neko Neko is offline
Neko
 
Join Date: Oct 2000
Posts: 8,619
Quote:
Originally Posted by Lupin View Post
I've been looking into deep learning for a while now, and I think I have a good grasp of the general picture.
The best resource I found so far is this online book: http://neuralnetworksanddeeplearning.com/
There's definitely a bit of math there, but it's quite manageable.

I also find the TensorFlow playground useful to help visualize what's actually happening.

TensorFlow is actually not bringing much new stuff to the table, it's main value is in providing a framework that works both for production and research, while most other older frameworks are research-oriented. It's also got better tooling. But the important stuff is in the math, not in the particular framework you use.

There are 2 important things to grasp in my experience to get a good grasp of the whole picture.
The first is the idea of Machine Learning in general and particularly the role of the "optimization/cost function" in learning.
The second is to get a good intuition for neural networks (both biological and artificial ones). NNs are not new stuff, even Deep Neural Networks, and they are a quite straight-forward model of what's inside our actual brains.

The field is quite complex, definitely not something you can learn overnight. But it's moving very very fast, and I'm pretty sure we're facing a revolution of the same magnitude as personal computing or the internet.

Particularly, the last developments from DeepMind (Atari games, AlphaGo) are a very significant step towards artificial general intelligence (AGI).
Self-driving cars, the Falcon 9 landings, as well as many huge tech successes of the recent years all gravitate around similar ideas and techniques.
The DeepMind paper about Atari games is mind-blowing, even if you don't go through the math in details.

Heavy progress seem to be made when there's a cross-pollination of ideas between state of the art neuroscience and comp-sci. We're in for an interesting decade.
I think i need to update my math
Reply With Quote
  #11  
Old 2016-05-25, 18:35
Darkflame's Avatar
Darkflame Darkflame is offline
Classic
 
Join Date: Feb 2001
Location: Sol, Earth, NL
Posts: 22,496
Send a message via ICQ to Darkflame Send a message via AIM to Darkflame Send a message via MSN to Darkflame
Quote:
The field is quite complex, definitely not something you can learn overnight. But it's moving very very fast, and I'm pretty sure we're facing a revolution of the same magnitude as personal computing or the internet.
Agreed. In fact, I think any child or student right now would be wise to consider learning this stuff with a mind to future careers. Its going to become the main method to get non-trival computer tasks done I think.

Of, course, it goes the other way too; Id advise people to get into bio engineering. Coding gene strands to create custom organisms. There is strong analogies between bio-engineering and early computing right now.

Quote:
Heavy progress seem to be made when there's a cross-pollination of ideas between state of the art neuroscience and comp-sci.
Very much so.
But needs to be a little bit of caution as to what we already know. I see some news/blogs etc inferring the main difference between the brain and computer neural networks is merely numbers.
But even a single neuron we dont fully know how to simulate so its not just scaling.
I think it was only in the last few years we have started to look at the mechanical effects as well as the bio-electrical ones.
__________________
http://fanficmaker.com <-- Tells some truly terrible tales.
-
Phones & Tricorders & Blobs & Bombs & 3D Printers & TVIntros also;stuff
Reply With Quote
  #12  
Old 2016-05-26, 01:07
Polaris's Avatar
Polaris Polaris is offline
Polly parrot
 
Join Date: Jan 2007
Location: Tippett Island
Posts: 5,671
Your first post reminded me of a video I found a while ago, Jesse. The AI also learns playing (this time on a NES), but the guy has an algorithm which lets his AI play different games without the need of modifying it.
https://www.youtube.com/watch?v=xOCurBYI_gY
__________________
<((((((((((((([[[========================]]])))))))))))))>

Last edited by Polaris; 2016-05-26 at 01:16.
Reply With Quote
  #13  
Old 2016-05-26, 10:17
Homeless's Avatar
Homeless Homeless is offline
Zebrazilla
 
Join Date: Oct 2002
Posts: 3,935
Quote:
Originally Posted by Polaris View Post
Your first post reminded me of a video I found a while ago, Jesse. The AI also learns playing (this time on a NES), but the guy has an algorithm which lets his AI play different games without the need of modifying it.
https://www.youtube.com/watch?v=xOCurBYI_gY
That was lovely, thank you for sharing.
__________________

LBA Speedruns
Personal Best - LBA 1 - Any% PC - Time: 01h 04m 23s
Personal Best - LBA 1 - Any% Android - Time: 01h 04m 35s
Reply With Quote
  #14  
Old 2016-05-26, 11:37
Polaris's Avatar
Polaris Polaris is offline
Polly parrot
 
Join Date: Jan 2007
Location: Tippett Island
Posts: 5,671
There's three episodes of that, the AI plays a shmup absolutely amazingly in the third one !
__________________
<((((((((((((([[[========================]]])))))))))))))>
Reply With Quote
  #15  
Old 2016-05-27, 13:31
Neko's Avatar
Neko Neko is offline
Neko
 
Join Date: Oct 2000
Posts: 8,619
Quote:
Originally Posted by Polaris View Post
There's three episodes of that, the AI plays a shmup absolutely amazingly in the third one !
will check it out tonight!

I am planning to train the network shown in video 1 to play ghostvalley course

edit: looks like the mario kart version of Mari/o isn't open sourced :\

Last edited by Neko; 2016-05-27 at 14:47.
Reply With Quote
  #16  
Old 2016-05-27, 20:24
Neko's Avatar
Neko Neko is offline
Neko
 
Join Date: Oct 2000
Posts: 8,619
Got the mari/o program to work
Reply With Quote
  #17  
Old 2016-05-28, 02:57
Darkflame's Avatar
Darkflame Darkflame is offline
Classic
 
Join Date: Feb 2001
Location: Sol, Earth, NL
Posts: 22,496
Send a message via ICQ to Darkflame Send a message via AIM to Darkflame Send a message via MSN to Darkflame
cool
__________________
http://fanficmaker.com <-- Tells some truly terrible tales.
-
Phones & Tricorders & Blobs & Bombs & 3D Printers & TVIntros also;stuff
Reply With Quote
  #18  
Old 2016-05-29, 14:26
Neko's Avatar
Neko Neko is offline
Neko
 
Join Date: Oct 2000
Posts: 8,619
So I have a generation that knows how to play level 1. It is currently training level 2. I wonder if it still can finish level 1 when it can finish level 2.
Reply With Quote
  #19  
Old 2016-05-29, 15:51
Polaris's Avatar
Polaris Polaris is offline
Polly parrot
 
Join Date: Jan 2007
Location: Tippett Island
Posts: 5,671
You mean that's downloadable ?! I need to check that out !
__________________
<((((((((((((([[[========================]]])))))))))))))>
Reply With Quote
  #20  
Old 2016-05-29, 16:15
Neko's Avatar
Neko Neko is offline
Neko
 
Join Date: Oct 2000
Posts: 8,619
yeah you can. but the inputs are not equal to what we see. it sees all enemies the same regardless of state, type and size. that doesn't seem fair.

So my next idea is to alter the script so it gets the right input.

Last edited by Neko; 2016-05-30 at 15:36.
Reply With Quote
  #21  
Old 2016-06-02, 09:35
Neko's Avatar
Neko Neko is offline
Neko
 
Join Date: Oct 2000
Posts: 8,619
I wonder if we could alter it also so it runs in parallel. Now it goes too slow. You would want to run an entire generation run in parallel
Reply With Quote
  #22  
Old 2016-06-03, 17:41
Polaris's Avatar
Polaris Polaris is offline
Polly parrot
 
Join Date: Jan 2007
Location: Tippett Island
Posts: 5,671
May I ask where you downloaded it ? There's a link to the source code under the video, but I don't know what to do with that
__________________
<((((((((((((([[[========================]]])))))))))))))>
Reply With Quote
  #23  
Old 2016-06-05, 19:03
Neko's Avatar
Neko Neko is offline
Neko
 
Join Date: Oct 2000
Posts: 8,619
1. download bizzhwawk emulator
2. save the sourcecode in a file called neatevolve.lua in the lua/snes folder
3. get the amarican super mario world rom
4. save a state
5. save the state file in the lua/snes folder and rename it DP1.state

bingo!
Reply With Quote
  #24  
Old 2016-06-05, 22:29
Polaris's Avatar
Polaris Polaris is offline
Polly parrot
 
Join Date: Jan 2007
Location: Tippett Island
Posts: 5,671
You're the best
__________________
<((((((((((((([[[========================]]])))))))))))))>
Reply With Quote
  #25  
Old 2016-06-05, 23:05
Styx's Avatar
Styx Styx is offline
Panta rei
 
Join Date: Mar 2006
Location: Constantly moving
Posts: 689
Quote:
Originally Posted by Jesse View Post
1. download bizzhwawk emulator
2. save the sourcecode in a file called neatevolve.lua in the lua/snes folder
3. get the amarican super mario world rom
4. save a state
5. save the state file in the lua/snes folder and rename it DP1.state

bingo!
Quote:
Originally Posted by Polaris View Post
You're the best
Did I miss some context or what?
__________________
Everything begins with a choice
Reply With Quote
Reply

Thread Tools

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump

Similar Threads
Thread Thread Starter Forum Replies Last Post
Deep breath - Let's Talk iPad Cyberg-Ares Off topic 30 2010-02-10 19:46
Rosseta Stone learning program Dino-Fly Off topic 20 2007-09-29 23:04
I'm thinking about learning how to create Neko Off topic 12 2006-02-01 19:20
In The Deep End - Chapter One Snapman Fan Fics 13 2002-08-22 22:55
Learning better English by MBN'ing wacko Off topic 13 2001-06-02 22:18


All times are GMT +2. The time now is 01:09.


News Feed
Powered by vBulletin®
Copyright ©2000 - 2021, Jelsoft Enterprises Ltd.
Copyright ©2000 - 2021, the Magicball Network