Artificial Inteligence in ComputerCraft - NeuralNetworks
#21
Posted 11 October 2015 - 06:35 AM
#22
Posted 11 October 2015 - 08:49 AM
#24
Posted 11 October 2015 - 08:57 AM
#25
Posted 11 October 2015 - 09:06 AM
#26
Posted 11 October 2015 - 09:42 AM
I now realize I should have let the dem in the gif run longer.
Edited by Creator, 11 October 2015 - 09:42 AM.
#28
Posted 11 October 2015 - 02:45 PM
#29
Posted 11 October 2015 - 03:12 PM
#30
Posted 11 October 2015 - 03:46 PM
What kind of assistant?
#32
Posted 11 October 2015 - 03:53 PM
Creator, on 11 October 2015 - 02:45 PM, said:
#33
Posted 11 October 2015 - 03:55 PM
Edited by gollark8, 11 October 2015 - 03:55 PM.
#34
Posted 11 October 2015 - 04:15 PM
#35
Posted 11 October 2015 - 05:06 PM
By the way, is there documentation available?
#36
Posted 11 October 2015 - 05:14 PM
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
Posted 11 October 2015 - 08:09 PM
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
Posted 11 October 2015 - 08:11 PM
#39
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
Posted 11 October 2015 - 08:53 PM
Creator, on 11 October 2015 - 08:11 PM, said:
Creator, 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