Jump to content




Artificial Inteligence in ComputerCraft - NeuralNetworks


146 replies to this topic

Poll: Artificial Inteligence in ComputerCraft - NeuralNetworks

Do you like the idea?

You cannot see the results of the poll until you have voted. Please login and cast your vote to see the results of this poll.

Do you like this implemetation?

You cannot see the results of the poll until you have voted. Please login and cast your vote to see the results of this poll.
Vote Guests cannot vote

#21 クデル

  • Members
  • 349 posts

Posted 11 October 2015 - 06:35 AM

I know a little bit about neural networks, and I love your work, but what does it "learn" from the input?

#22 Creator

    Mad Dash Victor

  • Members
  • 2,168 posts
  • LocationYou will never find me, muhahahahahaha

Posted 11 October 2015 - 08:49 AM

It learns from back propagation. You basically give it the expected result and it adjusts.

#23 クデル

  • Members
  • 349 posts

Posted 11 October 2015 - 08:55 AM

View PostCreator, on 11 October 2015 - 08:49 AM, said:

It learns from back propagation. You basically give it the expected result and it adjusts.

Adjusts, in hoping that it can anticipate the next result based on the two previously inputted numbers?

#24 Creator

    Mad Dash Victor

  • Members
  • 2,168 posts
  • LocationYou will never find me, muhahahahahaha

Posted 11 October 2015 - 08:57 AM

Yeah kinda.

#25 クデル

  • Members
  • 349 posts

Posted 11 October 2015 - 09:06 AM

Neat, good job! +1 :D

#26 Creator

    Mad Dash Victor

  • Members
  • 2,168 posts
  • LocationYou will never find me, muhahahahahaha

Posted 11 October 2015 - 09:42 AM

Thanks.

I now realize I should have let the dem in the gif run longer.

Edited by Creator, 11 October 2015 - 09:42 AM.


#27 Lupus590

  • Members
  • 2,029 posts
  • LocationUK

Posted 11 October 2015 - 02:43 PM

I'm trying to think of a MC application for this, perhaps task prioritisation in Hive? I know that neural networks are used for fussy data (something that doesn't exist in any game) so maybe there are none for MC? Turtle learning?

#28 Creator

    Mad Dash Victor

  • Members
  • 2,168 posts
  • LocationYou will never find me, muhahahahahaha

Posted 11 October 2015 - 02:45 PM

I have not thought about Hive. Maybe that'll will work. Could I help with the project in General?

#29 Creeper9207

  • Members
  • 211 posts

Posted 11 October 2015 - 03:12 PM

I wonder how this could be used to make an assistant

#30 Creator

    Mad Dash Victor

  • Members
  • 2,168 posts
  • LocationYou will never find me, muhahahahahaha

Posted 11 October 2015 - 03:46 PM

Difficultly?

What kind of assistant?

#31 H4X0RZ

  • Members
  • 1,315 posts
  • LocationGermany

Posted 11 October 2015 - 03:50 PM

View PostCreator, on 11 October 2015 - 03:46 PM, said:

Difficultly?

What kind of assistant?
I guess he's talking about something like Siri.

#32 Lupus590

  • Members
  • 2,029 posts
  • LocationUK

Posted 11 October 2015 - 03:53 PM

View PostCreator, on 11 October 2015 - 02:45 PM, said:

I have not thought about Hive. Maybe that'll will work. Could I help with the project in General?
The project is at a stand still at the moment, I'm thinking of changing how collaborators add code. Jump into gitter and we'll talk more.

#33 gollark8

  • Members
  • 207 posts

Posted 11 October 2015 - 03:55 PM

Having seen this, I'm wondering about using this to make a turtle find optimal strategies for mining, by having the neural network's numbers be used as turtle action codes, and having all the turtle's actions being back-propagated into the network after it finds ore.

Edited by gollark8, 11 October 2015 - 03:55 PM.


#34 Creator

    Mad Dash Victor

  • Members
  • 2,168 posts
  • LocationYou will never find me, muhahahahahaha

Posted 11 October 2015 - 04:15 PM

Omg, that is smart! I could help you implementing it.

#35 gollark8

  • Members
  • 207 posts

Posted 11 October 2015 - 05:06 PM

How can I save the neural network state to a file? Textutils serialisation?

By the way, is there documentation available?

#36 Creator

    Mad Dash Victor

  • Members
  • 2,168 posts
  • LocationYou will never find me, muhahahahahaha

Posted 11 October 2015 - 05:14 PM

1. I will be writing code allowing you to save it to a file.

2. All the explanation needed is in the description. If you still do not understand something, just post it here and I will respond.

PS: This is my 1111th post. Yay.

Textutils is not possible since the network is not a table, but rather a class system, which has locals.

Edited by Creator, 11 October 2015 - 05:16 PM.


#37 gollark8

  • Members
  • 207 posts

Posted 11 October 2015 - 08:09 PM

The API is giving me horribly useless errors. "Mate you are coding like a girl" is no use whatsoever when you're trying to debug code.

Edit: {5,5,5} neural net, feed-forwarding random numbers from 1 to 10 in every cycle, math.ceil()-ing the result, and I'm constantly getting 1.

Edited by gollark8, 11 October 2015 - 08:45 PM.


#38 Creator

    Mad Dash Victor

  • Members
  • 2,168 posts
  • LocationYou will never find me, muhahahahahaha

Posted 11 October 2015 - 08:11 PM

The issue is that when you call the feedforward function, you have to give a table as an argument. That table should contain the same amount of numbers as the input layer has neurons.

#39 Creator

    Mad Dash Victor

  • Members
  • 2,168 posts
  • LocationYou will never find me, muhahahahahaha

Posted 11 October 2015 - 08:17 PM

myNet = AI.Net({2,4,1})
myNet.feedForward({1,0})

There are 2 elements in the table given as an argument to the second function like there are two input neurons.

#40 gollark8

  • Members
  • 207 posts

Posted 11 October 2015 - 08:53 PM

View PostCreator, on 11 October 2015 - 08:11 PM, said:

The issue is that when you call the feedforward function, you have to give a table as an argument. That table should contain the same amount of numbers as the input layer has neurons.

View PostCreator, on 11 October 2015 - 08:17 PM, said:

myNet = AI.Net({2,4,1})
myNet.feedForward({1,0})

There are 2 elements in the table given as an argument to the second function like there are two input neurons.

In that case, it should give me that as an error, not what it gave me.





1 user(s) are reading this topic

0 members, 1 guests, 0 anonymous users