Àüü 4 page Áß 1 page±îÁö ¹Ì¸®º¸±â°¡ °¡´ÉÇÕ´Ï´Ù.
¼Ò°³±Û
Á¦¸ñ : µ¿Àû½Ã½ºÅÛ Á¦¾î¸¦ À§ÇÑ ´Ù´Üµ¿Àû ´º·Î-ÆÛÁö Á¦¾î±â ¼³°è
ÀúÀÚ : Á¶Çö¼·, ¹ÎÁø°æ
¹ßÇàÇÐȸ : Çѱ¹»êÇбâ¼úÇÐȸ [The Korea Academia-industrial cooperation Society]
¹ßÇàÁ¤º¸ : Ãá°è Á¦ 0±Ç 0È£ pp.150-153(4 pages)
¹ßÇà³âµµ : 2007
ÀúÀ۽ñâ : 2007³â
¸ñÂ÷
Abstract
1. Introduction
2. Structure of Neural Network
3. Learning Algorithm for MDNN Controller
4. Computer Simulation
5. Conclusion
Reference
º»¹®³»¿ë
The intent of this paper is to
describe a neural network structure called multi dynamic neural network(MDNN), and examine how it can be used in developing a learning scheme for computing robot inverse kinematic transformations. The architecture and learning algorithm of the proposed dynamic neural network structure, the MDNN, are described. Computer simulations are demonstrate the effectiveness of the proposed learning using the MDNN. (ÀÌÇÏ »ý·«)
Âü°í¹®Çå
¾øÀ½
¹ÞÀº º°Á¡
0/5
0°³ÀÇ º°Á¡
¹®¼°øÀ¯ ÀڷḦ µî·ÏÇØ ÁÖ¼¼¿ä.
¹®¼°øÀ¯ Æ÷ÀÎÆ®¿Í Çö±ÝÀ» µå¸³´Ï´Ù.
Æ÷ÀÎÆ® : ÀÚ·á 1°Ç´ç ÃÖ´ë 5,000P Áö±Þ
Çö±Ý : ÀÚ·á 1°Ç´ç ÃÖ´ë 2,000¿ø Áö±Þ
ÀúÀÛ±Ç Á¤º¸
À§ Á¤º¸ ¹× °Ô½Ã¹° ³»¿ëÀÇ Áø½Ç¼º¿¡ ´ëÇÏ¿© ¾ÅÅ©Á¸Àº º¸ÁõÇÏÁö ¾Æ´ÏÇϸç, ÇØ´ç Á¤º¸ ¹× °Ô½Ã¹° ÀúÀ۱ǰú ±âŸ ¹ýÀû Ã¥ÀÓÀº ÀÚ·á µî·ÏÀÚ¿¡°Ô ÀÖ½À´Ï´Ù.
À§ Á¤º¸ ¹× °Ô½Ã¹° ³»¿ëÀÇ ºÒ¹ýÀû ÀÌ¿ë, ¹«´Ü ÀüÀ硤¹èÆ÷´Â ±ÝÁöµÇ¾î ÀÖ½À´Ï´Ù.
ÀúÀÛ±ÇħÇØ, ¸í¿¹ÈÑ¼Õ µî ºÐÀï¿ä¼Ò ¹ß°ß½Ã °í°´¼¾ÅÍÀÇ ÀúÀÛ±Ç Ä§ÇØ½Å°í¸¦ ÀÌ¿ëÇØ Áֽñ⠹ٶø´Ï´Ù.
ºê·£µå Á¤º¸
°í±Þ ³í¹®À» Á¦°øÇÏ´Â ÇÐÁö»ç ´º³í¹®Àº Àü¹® Çо÷ ºÐ¾ß¿¡ ÃÖ°íÀÇ ÀڷḦ º¸ÀåÇϸç
°¢Á¾ ¿¬±¸ »ç·Ê¿Í ¹Ì·¡ ºÐ¼® µîÀÇ ÀڷḦ ÅëÇØ Àι®ÇÐ, »çȸ ÀÚ¿¬°úÇÐ ºÐ¾ßÀÇ ±íÀÌ Àִ Ž»öÀ» ÇÒ ¼ö ÀÖ°Ô µµ¿Íµå¸®°Ú½À´Ï´Ù.
ÆǸÅÀÚ·á ¼ö : 32,704°Ç