Search found 28 matches

by SirRanjid
Fri Apr 13, 2018 1:51 pm
Forum: Libraries and Tools
Topic: Artificial Neural Networks for lua
Replies: 5
Views: 289

Re: Artificial Neural Networks for lua

I bet^^. I think K-means is something I already got. I'm more about trying to make an AI that could really kick some ass and be fun to play against with. Or imagine a simple zombie ai which is driven by a neural net. For each zombie just apply some small random jitter to the weights and it seems lik...
by SirRanjid
Wed Apr 11, 2018 8:52 pm
Forum: Libraries and Tools
Topic: Artificial Neural Networks for lua
Replies: 5
Views: 289

Re: Artificial Neural Networks for lua

If you get a chance, initialize a large hidden layer with random values, and then attempt to just train the output layer. Drop out is also an interesting topic to explore on that front. Sounds interesting. Dropout was actually something I wanted to implement. At the moment I got momentum/velocity. ...
by SirRanjid
Wed Apr 11, 2018 6:47 pm
Forum: Libraries and Tools
Topic: Artificial Neural Networks for lua
Replies: 5
Views: 289

Artificial Neural Networks for lua

Hi was being asked to talk a bit more about my implementation of ANN here in lua. Actually already wrote this but when I tried attching a file via drag&drop(over the ad file button instead of the text entry) so my browser made the tab a download tab for my local file and everything got deleted for m...
by SirRanjid
Sat Mar 31, 2018 1:21 pm
Forum: Games and Creations
Topic: Planets (SIM)
Replies: 2
Views: 900

Re: Planets (SIM)

Thanks :) I also thought about them damaging each other but just went with a particle/shader effect. Actually I still wanna make them crack and fracture. But I can't edit the circle shapes and I'm not sure about using polygons(performance and looks wise). Yeah disabling fullscreen is just as DIY(in ...
by SirRanjid
Thu Mar 08, 2018 12:05 am
Forum: General
Topic: What's everyone working on? (tigsource inspired)
Replies: 1614
Views: 295740

Re: What's everyone working on? (tigsource inspired)

Implementing a neural network and backpropagation.

ImageImage
(Tries turning the net into a XOR function; line is the decreasing error)
by SirRanjid
Sat Feb 24, 2018 4:12 am
Forum: Games and Creations
Topic: Planets (SIM)
Replies: 2
Views: 900

Planets (SIM)

https://i.imgur.com/ioWP8qe.jpg Here's a small planet sim that's quite interactive. At first it was planned to be a doodle but it kept growing. Controls: [LM] = LEFt Mouse Button [RM] = RIGHT Mouse Button [MM] = MIDDLE Mouse Button [MWU]= Mouse Wheel UP [MWD]= Mouse Wheel DOWN [SH] = (L/R)Shift [CT...
by SirRanjid
Thu Feb 15, 2018 2:53 am
Forum: General
Topic: Code Doodles!
Replies: 146
Views: 36231

Re: Code Doodles!

Maybe not a doodle anymore but I've taken the fish to the next level.
Also cleaner and more commented code.

Image
by SirRanjid
Fri Feb 09, 2018 3:49 pm
Forum: General
Topic: Code Doodles!
Replies: 146
Views: 36231

Re: Code Doodles!

Flow field with some random squre fish things.

You can drag the background with left mouse and apply some movement like scrolling with your smartphone.

Image
flow_field.love
(3.22 KiB) Downloaded 29 times
by SirRanjid
Fri Jan 12, 2018 3:55 pm
Forum: General
Topic: [HELP]Rotating circles around the middle and not corner
Replies: 4
Views: 427

Re: [HELP]Rotating circles around the middle and not corner

That it's rotating around the upper left corner is good because it's the origin(x=0 and y=0). Just translate the origin to the desired position the way you're doing it. Or if you wanna have rotation and translation in the same line: planetX = math.cos(angle) * rotation_radius + rotation_center_offse...
by SirRanjid
Thu Jan 11, 2018 11:39 am
Forum: Support and Development
Topic: Multicore/Threading help?
Replies: 7
Views: 608

Re: Multicore/Threading help?

The snowflakes-eyecandy example was just an easy example i made up without testing mostly to get the concept right. Reading that it probably works serves it's purpose. But how is it unoptimal? Unoptimal in the sense of rather don't use threads here or can I actually improve the code above to be fast...