|
|
|
|
| LEADER |
00000naa a2200000 a 4500 |
| 003 |
AR-LpUFIB |
| 005 |
20250423183314.0 |
| 008 |
230201s2007 ag r 000 0 spa d |
| 024 |
8 |
|
|a DIF-M3115
|b 3220
|z DIF008326
|
| 040 |
|
|
|a AR-LpUFIB
|b spa
|c AR-LpUFIB
|
| 100 |
1 |
|
|a Vinuesa, Hernán
|9 46409
|
| 245 |
1 |
0 |
|a Neural Networks Elitist Evolution
|
| 300 |
|
|
|a Datos electrónicos (1 archivo: 208 KB)
|
| 500 |
|
|
|a Formato de archivo: PDF. -- Este documento es producción intelectual de la Facultad de Informática-UNLP (Colección BIPA / Biblioteca.)
|
| 520 |
|
|
|a This paper presents an elitist evolving strategy, which allows obtaining a controller, based on a neural network capable of commanding an autonomous robot. In order to reduce the detrimental crossover effect, we propose to use a strategy to create several children for each parent pair, selecting properly the way of making the replacement. The results obtained that, though the number ofchildren is high, the quantity of fitness tests carried out is actually lower than that of aconventional evolving algorithm. In this way, we propose an alternative that reduces thecomputational cost of the process, reaching at a suitable response for the problem resolution.
|
| 534 |
|
|
|a International Conference on Information Technology Interfaces (29th : 2007 : Duvrovnik)
|
| 650 |
|
4 |
|a ROBÓTICA
|9 42942
|
| 700 |
1 |
|
|a Lanzarini, Laura Cristina
|9 43377
|
| 942 |
|
|
|c CP
|
| 952 |
|
|
|0 0
|1 0
|4 0
|6 A0228
|7 3
|9 84637
|a DIF
|b DIF
|d 2025-03-11
|l 0
|o A0228
|r 2025-03-11 17:05:37
|w 2025-03-11
|y CP
|
| 999 |
|
|
|c 58095
|d 58095
|
