Tumblelog by Soup.io
Newer posts are loading.
You are at the newest post.
Click here to check if anything new just came in.

April 23 2014

pumuckl
Twisted Chain Drive in action
Reposted fromderreisende derreisende viametalab metalab
pumuckl
4330 3f55
Reposted fromzwiebelmann zwiebelmann viaclifford clifford
pumuckl
This scenario is the continuation of the previous "Deliver the ammo 1". It's sole purpose is to check if they actually seek the facilities and enemies because sometimes they are actually reacting to rather strange circumstances. Changing scenario dimensions is a good check for that.
Reposted fromkallaballa kallaballa
pumuckl
pumuckl

http://en.wikipedia.org/wiki/Bob_Widlar

Very interesting thanks for sharing!
Reposted frombons bons
pumuckl
Last week i changed the rules fundamentally. Now the space ships have finite fuel and ammo and they die when they are out of fuel. So i added "facilities" which they must use to recharge themselves.
To make them learn to recharge i gave them only a very small amount of fuel and no ammo in the beginning - so either they find the facility quickly or they die.
Additionally enemy facilities may be captured if the amount of enemy ships in range is greater by 3 than the amount of friendly ships in range but neither have i adjusted the fitness function nor did i train them yet to do so.
Reposted fromkallaballa kallaballa

April 07 2014

pumuckl
5673 646a
Reposted fromgifluv gifluv viaclifford clifford

April 05 2014

pumuckl

A video of  a lightly trained Neurocid population. Neurocid is a space ship battle simulation controlled by neural networks, evolved through a genetic algorithm.

I've trained them for about 15 minutes with smaller scenarios. I'll post videos of the training soon.


http://github.com/kallaballa/Neurocid  
Reposted fromkallaballa kallaballa
pumuckl

Lesson 2 of my neural network space battle simulation. In this lesson they should learn to hold their fire until they are in range.

http://github.com/kallaballa/Neurocid  

Reposted fromkallaballa kallaballa
pumuckl

Lesson 1 of the training for my neural network space battle simulation.
At this point the are completely untrained.

http://github.com/kallaballa/Neurocid  

Reposted fromkallaballa kallaballa

April 04 2014

pumuckl
A video of my neural network space simulation. The networks are trained using a genetic algorithm.

http://github.com/kallaballa/TankWar
Reposted fromkallaballa kallaballa

March 17 2014

6695 11bb

theclearlydope:

Well … well that’s just impressive. 

Reposted fromnajmetender najmetender viaastrid astrid

February 28 2014

pumuckl
Play fullscreen
Reposted frombina bina viam68k m68k

February 24 2014

pumuckl
pumuckl
Reposted frompsychob psychob viaclifford clifford

February 22 2014

pumuckl
Play fullscreen
Franz Reichelt, also known as Frantz Reichelt[1] or François Reichelt (1879 – February 4, 1912), was an Austrian-born French tailor, inventor and parachuting pioneer, now sometimes referred to as the Flying Tailor, who is remembered for his accidental death by jumping from the Eiffel Tower while testing a wearable parachute of his own design.

YOLO!  

February 19 2014

pumuckl
6826 4591
Reposted fromverschwoerer verschwoerer viagruetze gruetze

February 16 2014

pumuckl
Alexi Starovoitov has published an LLVM backend targeting an extended version of the Linux Kernel's BPF. An example of the sort of program that might be compiled and run via BPF can be found here.
LLVM Project Blog: LLVM Weekly - #6, Feb 10th 2014
Reposted fromclifford clifford
7882 5848

tits-mcgeek:

ladylestat88:

OMG!

Cosplay: you’re doing it right.

Reposted fromhennaflower hennaflower viaclifford clifford
Older posts are this way If this message doesn't go away, click anywhere on the page to continue loading posts.
Could not load more posts
Maybe Soup is currently being updated? I'll try again automatically in a few seconds...
Just a second, loading more posts...
You've reached the end.

Don't be the product, buy the product!

Schweinderl