neat : NEAT Users Group

Activity within 7 days:

Description

This group is for users of NEAT (NeuroEvolution of Augmenting Topologies), the neuroevolutionary technique created by Kenneth Stanley of the University of Texas at Austin.

The intent is to share ideas, questions, and comments regarding the implementation, theory, and possible variations and future directions of NEAT.

Most Recent Messages

(View All)
(Group by Topic)

Advanced

Start Topic

Re: Example of Training based on a DataSet Major bug in my code when setting input array values: for (Int32 j = 0; j < box.InputCount; j++) { box.InputSignalArray[0] = Convert.ToDouble(dr[j]); } should Posted - Mon Feb 13, 2012 5:30 pm	gotnobluemilk Offline Send Email
Re: Fitness Function As additional information to my stated problem, the best genome and connections I show are from generation 3821. Also, the genomes do complex, but then Posted - Sat Feb 11, 2012 1:56 pm	gotnobluemilk Offline Send Email
Fitness Function I am testing NEAT against the problem of detecting fraud. My approach is different than many of the examples because it is not a robot/game approach where you Posted - Sat Feb 11, 2012 1:46 pm	gotnobluemilk Offline Send Email
Re: Some Questions Regarding SharpNEAT v2 Changed the code to this: if (blackbox.OutputCount > 1) { // Read bias connection weight from output 1. double weight = outputSignalArr[1]; // Skip connections Posted - Wed Feb 8, 2012 12:31 am	gotnobluemilk Offline Send Email
Re: Some Questions Regarding SharpNEAT v2 ... So I would set OutputCount to 1, and also modify Substrate.cs so that it doesn't try to read the bias weight from output[1]. Basically you can comment out Posted - Tue Feb 7, 2012 9:12 am	Colin Green alienseedpod Offline Send Email
Add neat to your personalized My Yahoo! page What's This?

Message History

	Jan	Feb	Mar	Apr	May	Jun	Jul	Aug	Sep	Oct	Nov	Dec
2012	7	10
2011	29	13	27	59	15	24	18	14	17	12	59	26
2010	62	21	64	23	37	22	32	19	9	9	71	24
2009	16	47	14	46	48	28	70	37	33	4	91	79
2008	79	28	96	102	101	68	46	55	36	60	98	40
2007	20	67	103	137	140	68	38	71	22	47	38	66
2006	38	43	45	36	7	6	40	34	54	21	65	43
2005	68	32	40	19	47	41	120	83	67	76	77	25
2004	64	95	145	122	206	242	122	191	125	54	79	32
2003								41	63	88	42	66

Group Information

Yahoo! Groups Tips

Did you know...

Home

Activity within 7 days:

Description

Most Recent Messages

Message History

Questions in Science & Mathematics

Want to help answer other questions? Go to Yahoo! Answers

Yahoo! My Yahoo! Mail
	Sign In New User? Sign Up
		Tech - Groups - Help