±¹³»µµ¼
Àü°øµµ¼/´ëÇб³Àç
°øÇаè¿
ÄÄÇ»ÅÍ°øÇÐ
2013³â 9¿ù 9ÀÏ ÀÌÈÄ ´©Àû¼öÄ¡ÀÔ´Ï´Ù.
Á¤°¡ |
28,000¿ø |
---|
25,200¿ø (10%ÇÒÀÎ)
1,400P (5%Àû¸³)
ÇÒÀÎÇýÅÃ | |
---|---|
Àû¸³ÇýÅà |
|
|
|
Ãß°¡ÇýÅÃ |
|
À̺¥Æ®/±âȹÀü
¿¬°üµµ¼
»óÇ°±Ç
ÀÌ»óÇ°ÀÇ ºÐ·ù
Ã¥¼Ò°³
Ä¿³Î¿¬±¸È¸´Â ¸®´ª½º Ä¿³Î°ú ÀڷᱸÁ¶ ¾Ë°í¸®ÁòÀ» ¿¬±¸ÇÏ°í ¸®´ª½º ½Ã½ºÅÛ ÇÁ·Î±×·¡¹Ö ¹× µð¹ÙÀ̽ºµå¶óÀ̹ö °³¹ßÀ» ÅëÇÏ¿© âÀÇÀûÀÎ ÇÁ·ÎÁ§Æ®¸¦ ¼öÇàÇÏ¿© IoT °ü·Ã Á¦Ç°µéÀ» ¸¸µé¾î ÀÏ»ó »ýÈ°À» dz¿ä·Ó°í Æí¸®ÇÏ°Ô Çϴµ¥ °¡Ä¡¸¦ µÎ°í ÀÖ´Ù. ¾Æ¿ï·¯ °ü·Ã ±â¼úµéÀ» ±³À°ÇÏ¿© ¿©·¯»ç¶÷µé°ú °øÀ¯ÇÒ ¼ö ÀÖµµ·Ï ³ë·ÂÇÏ°í ÀÖ´Ù. ¡ºÁ÷Á¢ ÄÚµùÇÏ¸é¼ ¹è¿ì´Â ¸Ó½Å·¯´×/µö·¯´×¡»Àº 1ºÎ¿Í 2ºÎ·Î ³ª´©¾îÁ® ÀÖ´Ù. Á¦1ºÎ¿¡¼´Â ÅÙ¼Ç÷οì/ÆÄÀ̽ã ȯ°æ¿¡¼ ½Ç½ÀÇÏ¸é¼ ¸Ó½Å·¯´×À» ÀÌÇØÇÒ ¼ö ÀÖµµ·Ï ÇÏ¿´°í Á¦2ºÎ¿¡¼´Â C¾ð¾î·Î ¸Ó½Å·¯´× ¾Ë°í¸®ÁòÀ» Á÷Á¢ ÄÚµùÇÏ¸é¼ ÀÚ¼¼È÷ ÀÍÈú ¼ö ÀÖµµ·Ï ±¸¼ºÇß´Ù.
ÃâÆÇ»ç ¼Æò
Á¦1Àå¿¡¼´Â ¸Ó½Å·¯´×À» ÄÄÇ»ÅÍ¿¡¼ ½Ç½ÀÇÒ ¼ö ÀÖµµ·Ï °¢Á¾ ÆÐÅ°Áö ÇÁ·Î±×·¥À» ¼³Ä¡ÇÏ°í ȯ°æ¼³Á¤ÇÏ´Â ¹æ¹ý¿¡ ´ëÇؼ ±â¼úÇß´Ù.
Á¦2Àå¿¡¼´Â ¸Ó½Å·¯´× ±âº» ¾Ë°í¸®ÁòÀ» ÀÌÇØÇÒ ¼ö ÀÖµµ·Ï Çß°í,
Á¦3Àå ºÎÅÍ´Â Neural NetworkÀ» ¾î¶»°Ô ±¸¼ºÇÏ¿© µö·¯´×À» Àü°³ÇØ ³ª°¡´ÂÁö ÀÚ¼¼È÷ ¼³¸íÇÑ´Ù.
Á¦4ÀåÀº CNN ¾Ë°í¸®Áò¿¡¼ ¾î¶»°Ô ¿µ»óÀ̹ÌÁöµéÀ» ÀνÄÇÏ´ÂÁö ¼³¸íÇÏ°í,
Á¦5Àå¿¡¼´Â RNN ¾Ë°í¸®ÁòÀ» »ç¿ëÇÏ¿© ¹®ÀÚ¿Í À½¼º µ¥ÀÌÅ͸¦ ¾î¶»°Ô ÀνÄÇÏ´ÂÁö ¼³¸íÇÑ´Ù.
Á¦2ºÎ¿¡¼´Â C¾ð¾î·Î ¸Ó½Å·¯´× ¾Ë°í¸®ÁòÀ» Á÷Á¢ ÄÚµùÇÏ¸é¼ ÀÚ¼¼È÷ ÀÍÈú ¼ö ÀÖµµ·Ï ±¸¼ºÇß´Ù.
Á¦1ºÎ¿¡ ÀÖ´Â ÅÙ¼Ç÷οì´Â ¸Ó½Å·¯´× ¾Ë°í¸®ÁòÀ» ¶óÀ̺귯¸®¿¡ ±¸ÇöÇØ ³õ°í ±×°ÍÀÇ »ç¿ë¹ýÀ» ÀÍÈ÷¸é ½±°Ô »ç¿ëÇÒ ¼ö ÀÖ´Â ¹Ý¸é¿¡,
¾Ë°í¸®Áò ¼Ò½º°¡ ¶óÀ̺귯¸®¿¡ ¼û°ÜÁ® Àֱ⠶§¹®¿¡ Back Propogation°ú °°Àº Áß¿äÇÑ ¾Ë°í¸®ÁòÀº ÀÚ¼¼È÷ ºÐ¼®Çϱâ Èûµé´Ù.
±×·¡¼ ÇÊÀÚ´Â C¾ð¾î·Î ¸Ó½Å·¯´× ¾Ë°í¸®ÁòµéÀ» Çϳª¾¿ ÄÚµùÇØ °¡¸é¼ »ó¼¼È÷ ÀÍÈú ¼ö ÀÖµµ·Ï ³»¿ëÀ» ±¸¼ºÇß´Ù.
ÇÊÀÚÀÇ ÀÌ Ã¥Àº ¸Ó½Å·¯´× ¾Ë°í¸®ÁòÀ» óÀ½ºÎÅÍ ³¡±îÁö ÀÍÇô¼ ¾Ë°í¸®Áò ¼º´É °³¼±¿¡ ´ëÇؼ ¿¬±¸ÇÏ°íÀÚ ÇÏ´Â µ¶Àںе鿡°Ô ¾ÆÁÖ À¯¿ëÇÒ °ÍÀÌ´Ù.
Á¦2ºÎÀÇ Á¦6ÀåºÎÅÍ ¸Ó½Å·¯´× ¾Ë°í¸®ÁòµéÀ» C¾ð¾î·Î Çϳª¾¿ ÄÚµùÇÏ¸é¼ ±âº»±â¸¦ źźÈ÷ ÀÍÈ÷°í
Á¦7Àå¿¡¼´Â C¾ð¾î·Î Neural Network ¾Ë°í¸®ÁòÀ» ÄÚµùÇÑ´Ù.
À̸¦ ¹ÙÅÁÀ¸·Î Á¦8Àå¿¡¼ ¾ó±¼ÀÎ½Ä ¾Ë°í¸®Áò¿¡ ´ëÇؼ ¼³¸íÇÑ´Ù.
ÀÌ Ã¥ÀÇ ¸ðµç ¿¹Á¦ ¼Ò½ºµéÀº ¾Æ·¡ÀÇ GitHub »çÀÌÆ®¿¡¼ ´Ù¿î·Îµå ¹ÞÀ» ¼ö ÀÖ´Ù.
https://github.com/kernel-bz/ml
¸ñÂ÷
Á÷Á¢ ÄÚµùÇÏ¸é¼ ¹è¿ì´Â ¸Ó½Å·¯´×/µö·¯´× 1
ÀúÀÛ±Ç 2
Ä¿³Î¿¬±¸È¸ ·Îµå¸Ê 3
ÀúÀÚ ¼Ò°³ 4
¸ñÂ÷ 5
Á¦1ºÎ ÅÙ¼Ç÷οì/ÆÄÀ̽㠱â¹Ý ¸Ó½Å·¯´× 9
1. ¸Ó½Å·¯´× ½Ç½À ȯ°æ 10
1.1 ¸Ó½Å·¯´× ¼Ò°³ 10
1.2 ¸®´ª½º¿ë °³¹ßȯ°æ ¼³Ä¡ 16
1.3 À©µµ¿ì¿ë °³¹ßȯ°æ ¼³Ä¡ 20
1.4 TENSORFLOW 񃧯 21
2. ¸Ó½Å·¯´× ¾Ë°í¸®Áò 23
2.1 LINEAR REGRESSION 23
2.1.1 °¡¼³ÇÔ¼ö(ÇнÀ ¸ðµ¨)¿Í ºñ¿ëÇÔ¼ö 23
2.1.2 ºñ¿ë ÁÙÀ̱â(±â¿ï±â ¿¹Ãø) 30
2.1.3 ¹ÌºÐ ÇÔ¼ö(Convex) 32
2.2 LINEAR REGRESSION LEARNING 35
2.2.1 ´ÜÇ׺¯¼ö ±â¿ï±â ÇнÀ1 35
2.2.2 ´ÜÇ׺¯¼ö ±â¿ï±â ÇнÀ2 37
2.2.3 ´ÜÇ׺¯¼ö ±â¿ï±â ÇнÀ3 39
2.2.4 ´ÙÇ׺¯¼ö ±â¿ï±â ÇнÀ 41
2.2.5 ´ÙÇ׺¯¼ö ¸ÅÆ®¸¯½º ó¸® 44
2.2.6 ´ÙÇ׺¯¼ö ÆÄÀÏ Àбâ 47
2.3 LOGISTIC(BINARY) CLASSIFICATION 51
2.3.1 ÇнÀ ¸ðµ¨(Hypothesis) 51
2.3.2 ºñ¿ë ÇÔ¼ö 55
2.3.3 Logistic Regression 57
2.4 MULTINOMIAL(SOFTMAX) CLASSIFICATION 61
2.4.1 ÇнÀ ¸ðµ¨(Hypothesis) 61
2.4.2 Softmax ÇÔ¼ö 64
2.4.3 ºñ¿ë ÇÔ¼ö 67
2.4.4 TensorFlow ½Ç½À 69
3. DEEP LEARNING 77
3.1 µö·¯´× ±âº» 78
3.1.1 Çൿ ÇÔ¼ö 80
3.1.2 XOR ¹®Á¦ 80
3.1.3 Neural Network 82
3.1.4 Back Propagation 88
3.2 XOR ¹®Á¦ ÇØ°á ½Ç½À 93
3.2.1 ÀϹÝÀûÀÎ XOR ¹®Á¦ 93
3.2.2 XOR Neural Network 95
3.2.3 XOR Deep Learning 98
3.2.4 XOR Deep Learning2 105
3.2.5 XOR ReLU 108
3.3 µö·¯´× Á¤È®¼º Çâ»ó 110
3.3.1 ReLU 110
3.3.2 Good Weight (ÃʱⰪ) 112
3.3.3 Overfitting Á¶Á¤ 113
3.3.4 DropOut 114
3.3.5 Optimizer ¼º´É ºñ±³ 116
3.4 µö·¯´× ½Ç½À 117
3.4.1 ÀϹÝÀûÀÎ softmax 118
3.4.2 ReLU 121
3.4.3 DropOut 123
3.4.4 ÃʱⰪ ¼³Á¤ 126
3.4.5 °á°ú Á¤¸® 128
4. CONVOLUTIONAL NEURAL NETWORK 129
4.1 CONVOLUTION LAYER 129
4.2 POOLING LAYER 133
4.3 CNN Á¾·ù 136
4.3.1 AlexNet 136
4.3.2 GoogLeNet 136
4.3.3 ResNet 137
4.3.4 DeepMind AlphaGo 138
4.4 CNN ½Ç½À 139
4.4.1 Adam Optimizer 139
4.4.2 RMS Optimizer 144
4.4.3 °á°ú Á¤¸® 148
5. RECURRENT NEURAL NETWORK 149
5.1 RNN ÀÌÇØ 149
5.2 RNN È°¿ë 153
Á¦2ºÎ C¾ð¾î·Î ¸Ó½Å·¯´×/µö·¯´× ÄÚµùÇϱâ 154
6. ¸Ó½Å·¯´× ±âº» ¾Ë°í¸®Áò ÄÚµù 155
6.1 LINEAR REGRESSION 155
6.1.1 °¡¼³ÇÔ¼ö ¹× ºñ¿ëÇÔ¼ö ÄÚµù 156
6.1.2 ºñ¿ë »êÃâ Àüü ¼Ò½º 157
6.1.3 ÃÖ¼Òºñ¿ë »êÃâ ÇÔ¼ö ÄÚµù 163
6.1.4 ÇнÀÁøÇà ÇÔ¼ö ÄÚµù 165
6.1.5 ÇнÀÁøÇà Àüü ¼Ò½º 166
6.1.6 ¹ÌºÐÇÔ¼ö ÄÚµù 172
6.1.7 ¹ÌºÐ°ª »êÃâÇÔ¼ö ÄÚµù 179
6.2 ´ÙÇ׺¯¼ö ¸Ó½Å·¯´× 186
6.2.1 ´ÙÇ׺¯¼ö ÇнÀ ÄÚµù 186
6.2.2 ¸ÅÆ®¸¯½º(Çà¿) ÄÚµù 195
6.2.3 ¸ÅÆ®¸¯½º(Çà¿) ¹ÌºÐÇÔ¼ö º¯°æ 210
6.3 LOGISTIC(BINARY) CLASSIFICATION 218
6.3.1 ÇнÀ ¸ðµ¨ ÄÚµù 218
6.3.2 ºñ¿ë ÇÔ¼ö ÄÚµù 219
6.3.3 Logistic Regression 220
6.3.4 Àüü ½ÇÇà ¼Ò½º 224
6.4 MULTINOMIAL(SOFTMAX) CLASSIFICATION 231
6.4.1 ÇнÀ ¸ðµ¨(Hypothesis) 231
6.4.2 Softmax ÇÔ¼ö ÄÚµù 233
2.4.4 TensorFlow ½Ç½À 234
7. NEURAL NETWORK ¾Ë°í¸®Áò ÄÚµù 235
7.1 µ¥ÀÌÅÍ Àбâ 236
7.2 Àб⠽ÇÇà ¼Ò½º 241
7.3 Àб⠰á°ú 248
7.4 NEURAL NETWORK ÄÚµù 250
7.5 FORWARD PROPAGATION 251
7.6 BACK PROPAGATION 254
7.7 NEURAL NETWORK ¼Ò½º 260
7.8 ½ÇÇà °á°ú 271
8. ¾ó±¼ ÀÎ½Ä ¾Ë°í¸®Áò 275
8.1 ¾ó±¼ °ËÃâ ¾Ë°í¸®Áò 275
8.2 ¾ó±¼ ÇнÀ 310
ºÎ·ÏA. ¸Ó½Å·¯´× °ü·Ã ¿ÀǼҽºµé 313
ºÎ·ÏB. Ä¿³Î¿¬±¸È¸ ±³À°°úÁ¤ »ó¼¼¾È³» 314
B.1 Ä¿³Î¿¬±¸È¸ ±³À°°úÁ¤ ·Îµå¸Ê 314
B.2 C¾ð¾î¿Í ÀڷᱸÁ¶ ¾Ë°í¸®Áò 315
B.3 ¸®´ª½º ½Ã½ºÅÛ ÇÁ·Î±×·¡¹Ö 319
B.4 ARM ¾ÆÅ°ÅØÃÄ, STM32 ÇÁ·Î±×·¡¹Ö 323
B.5 ¸®´ª½º Ä¿³Î ÀڷᱸÁ¶ ¾Ë°í¸®Áò ½Ç½À 326
B.6 ¸®´ª½º Ä¿³Î ¼Ò½º µð¹ö±ë ½Ç½À 330
B.7 ¸®´ª½º Ä¿³Î DEVICE TREE ½Ç½À 334
B.8 ±³À° ³»¿ë Å×À̺í 338
ÁÖ°£·©Å·
´õº¸±â»óÇ°Á¤º¸Á¦°ø°í½Ã
À̺¥Æ® ±âȹÀü
Àü°øµµ¼/´ëÇб³Àç ºÐ¾ß¿¡¼ ¸¹Àº ȸ¿øÀÌ ±¸¸ÅÇÑ Ã¥
ÆǸÅÀÚÁ¤º¸
»óÈ£ |
(ÁÖ)±³º¸¹®°í |
---|---|
´ëÇ¥ÀÚ¸í |
¾Èº´Çö |
»ç¾÷ÀÚµî·Ï¹øÈ£ |
102-81-11670 |
¿¬¶ôó |
1544-1900 |
ÀüÀÚ¿ìÆíÁÖ¼Ò |
callcenter@kyobobook.co.kr |
Åë½ÅÆǸž÷½Å°í¹øÈ£ |
01-0653 |
¿µ¾÷¼ÒÀçÁö |
¼¿ïƯº°½Ã Á¾·Î±¸ Á¾·Î 1(Á¾·Î1°¡,±³º¸ºôµù) |
±³È¯/ȯºÒ
¹ÝÇ°/±³È¯ ¹æ¹ý |
¡®¸¶ÀÌÆäÀÌÁö > Ãë¼Ò/¹ÝÇ°/±³È¯/ȯºÒ¡¯ ¿¡¼ ½Åû ¶Ç´Â 1:1 ¹®ÀÇ °Ô½ÃÆÇ ¹× °í°´¼¾ÅÍ(1577-2555)¿¡¼ ½Åû °¡´É |
---|---|
¹ÝÇ°/±³È¯°¡´É ±â°£ |
º¯½É ¹ÝÇ°ÀÇ °æ¿ì Ãâ°í¿Ï·á ÈÄ 6ÀÏ(¿µ¾÷ÀÏ ±âÁØ) À̳»±îÁö¸¸ °¡´É |
¹ÝÇ°/±³È¯ ºñ¿ë |
º¯½É ȤÀº ±¸¸ÅÂø¿À·Î ÀÎÇÑ ¹ÝÇ°/±³È¯Àº ¹Ý¼Û·á °í°´ ºÎ´ã |
¹ÝÇ°/±³È¯ ºÒ°¡ »çÀ¯ |
·¼ÒºñÀÚÀÇ Ã¥ÀÓ ÀÖ´Â »çÀ¯·Î »óÇ° µîÀÌ ¼Õ½Ç ¶Ç´Â ÈÑ¼ÕµÈ °æ¿ì ·¼ÒºñÀÚÀÇ »ç¿ë, Æ÷Àå °³ºÀ¿¡ ÀÇÇØ »óÇ° µîÀÇ °¡Ä¡°¡ ÇöÀúÈ÷ °¨¼ÒÇÑ °æ¿ì ·º¹Á¦°¡ °¡´ÉÇÑ »óÇ° µîÀÇ Æ÷ÀåÀ» ÈѼÕÇÑ °æ¿ì ·½Ã°£ÀÇ °æ°ú¿¡ ÀÇÇØ ÀçÆǸŰ¡ °ï¶õÇÑ Á¤µµ·Î °¡Ä¡°¡ ÇöÀúÈ÷ °¨¼ÒÇÑ °æ¿ì ·ÀüÀÚ»ó°Å·¡ µî¿¡¼ÀÇ ¼ÒºñÀÚº¸È£¿¡ °üÇÑ ¹ý·üÀÌ Á¤ÇÏ´Â ¼ÒºñÀÚ Ã»¾àöȸ Á¦ÇÑ ³»¿ë¿¡ ÇØ´çµÇ´Â °æ¿ì |
»óÇ° Ç°Àý |
°ø±Þ»ç(ÃâÆÇ»ç) Àç°í »çÁ¤¿¡ ÀÇÇØ Ç°Àý/Áö¿¬µÉ ¼ö ÀÖÀ½ |
¼ÒºñÀÚ ÇÇÇغ¸»ó |
·»óÇ°ÀÇ ºÒ·®¿¡ ÀÇÇÑ ±³È¯, A/S, ȯºÒ, Ç°Áúº¸Áõ ¹× ÇÇÇغ¸»ó µî¿¡ °üÇÑ »çÇ×Àº¼ÒºñÀÚºÐÀïÇØ°á ±âÁØ (°øÁ¤°Å·¡À§¿øȸ °í½Ã)¿¡ ÁØÇÏ¿© ó¸®µÊ ·´ë±Ý ȯºÒ ¹× ȯºÒÁö¿¬¿¡ µû¸¥ ¹è»ó±Ý Áö±Þ Á¶°Ç, ÀýÂ÷ µîÀº ÀüÀÚ»ó°Å·¡ µî¿¡¼ÀǼҺñÀÚ º¸È£¿¡ °üÇÑ ¹ý·ü¿¡ µû¶ó ó¸®ÇÔ |
(ÁÖ)ÀÎÅÍÆÄÅ©Ä¿¸Ó½º´Â ȸ¿ø´ÔµéÀÇ ¾ÈÀü°Å·¡¸¦ À§ÇØ ±¸¸Å±Ý¾×, °áÁ¦¼ö´Ü¿¡ »ó°ü¾øÀÌ (ÁÖ)ÀÎÅÍÆÄÅ©Ä¿¸Ó½º¸¦ ÅëÇÑ ¸ðµç °Å·¡¿¡ ´ëÇÏ¿©
(ÁÖ)KGÀ̴Ͻýº°¡ Á¦°øÇÏ´Â ±¸¸Å¾ÈÀü¼ºñ½º¸¦ Àû¿ëÇÏ°í ÀÖ½À´Ï´Ù.
¹è¼Û¾È³»
±³º¸¹®°í »óÇ°Àº Åùè·Î ¹è¼ÛµÇ¸ç, Ãâ°í¿Ï·á 1~2Àϳ» »óÇ°À» ¹Þ¾Æ º¸½Ç ¼ö ÀÖ½À´Ï´Ù.
Ãâ°í°¡´É ½Ã°£ÀÌ ¼·Î ´Ù¸¥ »óÇ°À» ÇÔ²² ÁÖ¹®ÇÒ °æ¿ì Ãâ°í°¡´É ½Ã°£ÀÌ °¡Àå ±ä »óÇ°À» ±âÁØÀ¸·Î ¹è¼ÛµË´Ï´Ù.
±ººÎ´ë, ±³µµ¼Ò µî ƯÁ¤±â°üÀº ¿ìü±¹ Åù踸 ¹è¼Û°¡´ÉÇÕ´Ï´Ù.
¹è¼Ûºñ´Â ¾÷ü ¹è¼Ûºñ Á¤Ã¥¿¡ µû¸¨´Ï´Ù.