AlphaGo에서 시작하는 인공지능

AlphaGo, Alpha Zero에서 시작해서 여러 인공지능의 개념을 살펴봅니다.

Transcript

1. LEONARDO YONGUK KIM DALINAUM@GMAIL.COM ALPHAGOীࢲ द੘ೞח 
 ੋҕ૑מ
2. ALPHAGOোഄ AlphaG o Fan Goח ੌࠄয۽ ߄قਸ ੄޷ 2015 2016. 3. 9 AlphaG o Lee 2017. 5. 17 AlphaG o M aster AlphaG o Zero 2017. 10. 19 2018.12.7 Alpha Zero ౸ റ੉ (2ױ)җ ؀Ѿ೧ࢲ थܻ ੉ࣁج (9ױ)җ ؀Ѿ೧ࢲ थܻ 
 ੷੘ӂ ೧Ѿػ 16݅ ӝࠁ ೟ण. 48ѐ੄ TPU ৡۄੋ ؀Ҵ 60োथ ழઁীѱ थܻ 4ѐ੄ TPU. 10ߓ ীց૑ ബਯ ੋр੄ ૑धহ੉ (ӝࠁ X) ߄ق ੿ࠂ ঌ౵Ҋ ݃झఠ৬ ऱਕ 89थ 11ಁ ࣳӝ, ୓झ, झఋ 2 ੿ࠂ Goܳ ੉ܴীࢲ ઁ৻
3. ݾ಴ ࣻ ੍ӝ न҃ݎ ъച ೟ण ੋҕ૑מ ࢎਊ੄ ৘
4. ࣻ ੍ӝ MiniMax Monte Carlo Method Monte Carlo Tree Search
5. MINIMAX
6. TIC TAC TOE O O O X X O X O X X O X O - ݢ੷ 3ѐܳ աۆ൤ ֬਷ ࢎۈ੉ ੉ӝח ѱ੐ - ੉ ੿ب ࠂ੟ೠ ѱ੐਷ ݽٚ ҃਋੄ ࣻܳ ࠅ ࣻ ੓਺. - 9 x 8 x 7 x 6 x 5 x 4 x 3 x 2 = 9! O X O O X X O
7. O O O O O O O O O ROOT O X O X O X O X O X O X O X O X O X O O X O O X O O X O O X O O X O O X O ֢٘ 1 0 -1 0 -1 -1 ઺ۚ ܖ౟ ੉ӝݶ 1੼, ࠺ӝݶ 0੼,૑ݶ -1੼ ROOT੄ ੑ੢ীࢲ 
 ੗ध੉ۄҊب ೤פ׮. ݽٚ ֢٘ח ੗ध੉੗ ࠗݽੑפ׮.
8. O O O O O O O O O ROOT O X O X O X O X O X O X O X O X O X O O X O O X O O X O O X O O X O O X O ֢٘ 1 0 -1 0 -1 -1 ઺ۚ ܖ౟ MY TURN ௾ ੼ ࣻܳ ࢶఖೞҊ ੼ࣻо ੘਷ ࠳ے஖ܳ ઁѢ
9. O O O O O O O O O ROOT O X O X O X O X O X O X O X O X O X O O X O O X O O X O O X O O X O O X O ֢٘ ઺ۚ ܖ౟ YOUR TURN ੘਷ ੼ࣻܳ ࢶఖ 
 ௾ ੼ࣻо ੓ח ࠳ے஖ח ઁѢ
10. O O O O O O O O O ROOT O X O X O X O X O X O X O X O X O X O O X O O X O O X O O X O O X O O X O ઺ۚ MY TURN ௾ ੼ࣻܳ ࢶఖ
12. - (19 x 19)! - 19 x 19 = 361 - 361 x 360 x 359 x 358 …. x 2 - 26744876149564427899473201526425013452390919904351815721084971068304474 7437531294143149639831010372677443849403182318969228741381559487197927737 64930851408087543453474101182344879484162985721534603948370802204778391 45379274006646833128661312942336287321284636912937632439789397222224742 52826712518506072707918591157844247991603554375217925635775598044364577 67819229829195896785070533331329604395837235880245012197523337773352603 746540435758711323413067205097510873318696774954051195138779582025728045 717997197429383169516478847881483048003766654327470766455887103023601081 7570107837589904730596477443151082000948524919032642496288011069869044 42993333787797164945029657423253487692054233010201128993815319944149127 636942433924747935483481769568213401600000000000000000000000000000000 0000000000000000000000000000000000000000000000000000000000000000 ߄ق੄ ҃਋੄ ࣻ
13. MONTE CARLO METHOD
14. ਗ઱ਯਸ ੕য ࠇद׮ - ਗ઱ਯਸ ੕঻णפ׮. - ਗ઱ਯਸ ా҅੸ਵ۽ ҳೡ ࣻ ੓ਸөਃ?
15. MONTE CARLO METHOD - ےؒೞѱ ੼ਸ ନ਻द׮. - ਗ উ੄ ੼੄ іࣻо 314ѐ, ࢎпഋ উ੄ ੼੄ іࣻо 400ѐۄ о੿೧ ࠇद׮. - 4(R ^ 2) : π(R ^ 2) = 400 : 314, π = 3.14 - ୽࠙൤ ੼ਸ ݆੉ ନਸ ࣻ۾ ؊ ੿޻ೠ ਗ઱ਯਸ ঌѱ ؾפ׮.
16. ׮ ޅ ࠊب ݆੉ ࠁݶ 
 ੄޷੓૑ ঋਸө?
17. O O O O O O O O O ROOT ୐ ࣻ ੉റ ےؒਵ۽ 10౸ فয пп थܫਸ ҳೣ. 40% PLAYOUT 60% 30% 20% 80% 30% 20% 50% 10% - п ࣻ ݃׮ ੉റ, ےؒೞѱ 10౸ਸ فয (Playout) थܫਸ ҳೣ. (9 x 10 = 90౸) - थܫ੉ о੢ ֫਷ 5ߣ૩ ࣻ(80%)о ୭Ҋ৓׮Ҋ ౸ױೣ. - दр੉ ؊ ݆੉ ੓׮ݶ Playout੄ പࣻܳ ט۰ࢲ न܉بܳ ૐоदఆ ࣻ ੓਺. (100౸ فӝ) - Playout੄ പࣻо טযաݶ טযզ ࣻ۾ MiniMax੄ Ѿҗ৬ ਬࢎ೧૕ Ѫ੐. - Playout, Rollout, Simulation ١੄ ױযо ࢎਊ ؽ.
18. Ӓېب ୐ ࣻ ৻ী 
 ݽف ےؒ਷ ખ Ӓۧ૑ ঋաਃ?
19. MONTE CARLO TREE SEARCH
20. O O O O O O O O O ROOT 40% PLAYOUT 60% 30% 20% 80% 30% 20% 50% 10% - ےؒೞѱ فযࢲ थܫ੉ ֫਷ ࣻܳ ݢ੷ Ҋܵפ׮.
21. O O O O O O O O O ROOT - ੉ઁ थܫ੉ ֫਷ 5ߣ૩ ࣻ ਤ઱۽ ےؒ ؀Ѿਸ ೤פ׮. (70%) - աݠ૑ ٜࣻب ےؒ ؀Ѿਸ оՔ೤פ׮. (30%) - ֬஘ ࣻо ੓ӝ ٸޙੑפ׮.
22. O O O O O O O O O ROOT - 5ߣ૩ ࣻী ؀೧ যו ੿ب ےؒ ؀Ѿਸ ೮ਵݶ, 5ߣ૩ ࣻ੄ ੗धب ౟ܻী ನೣ೤פ׮. - ੉ઁ ےؒೞѱ ف૑݅ ୊਺ ف ࣻח Ҋ੿ೞҊ ೤פ׮. - ੼ର ৌ۰ ੓ח ֢٘о ݆ই ૘פ׮. X O X O X O O X X O O X O X O X
24. - ୓झח 1996֙ 2ਘ 10ੌ MiniMax ۽ ੿ࠂ. (गಌ ஹೊఠ ٩ ࠶ܖ) - ୭Ӕীח Monte Carlo Tree Search۽ ോ؀ಪਵ۽ب Ӓے٘݃झ ఠܳ ੉ӣ. - ೞ૑݅ ߄ق਷ ࠛоמ೮਺. - ഛܫ੸ਵ۽ ೞӝূ ڜࣻо ցޖ ݆ ਺. ࣻ ੍ӝ݅ਵ۽ ୽ ࠙ೠоਃ?
25. ੄޷ ੓ח Ҕ݅ 
 ٮઉࠁݶ উغਃ?
26. (ࢎۈ ࢤпী) ੄޷ ੓ח Ҕ݅ 
 ٮઉࠁݶ উغਃ?
27. न҃ݎ न҃ݎ CNN
28. न҃ݎ
29. ੹ӝ੸ नഐܳ ߉ই оҕ೧ ੹ӝ੸ नഐܳ ࠁղח Ѫ? ׏۠
30. X1 X2 Y W1 W2 Y = W1X1 + W2X2 ࣻ ݆਷ ׏۠੉ Ѿ೤೧ (֎౟ਕ௼) ૑מਸ ٜ݅যմ Ѫ ୊ۢ, ࣻ рױೠ о઺஖ ো࢑(ੋҕ ׏۠)ਸ ֎౟ਕ௼ܳ ٜ݅ݶ যڌѱ ؼөਃ?
31. - ೙ӝ୓ 0~9ܳ ޷Ҵ NISTо ࣻ૘. - о۽ 28, ࣁ۽ 28੄ ೗ࣄ۽ ҳࢿ. - ೠ Ӗ੗׼ 784 ೗ࣄ (28 x 28) MNIST
33. - ࡈр࢝਷ ੼੉ ੓ਵݶ উػ׮ח ڷ. - ౵ۆ࢝਷ ੼੉ ੓ਵݶ જ׮ח ڷ. - 0੄ о਍ؘח ੼੉ ੓ਵݶ উػ׮. - 1੄ о਍ؘח ੼੉ ੓ਸ оמࢿ੉ ֫ ਺. - ࡈъ਷ -1, ౵ی਷ 1۽ ࠁ੗. Ѩ਷ ࢝ ਷ 0 ೙ӝ୓ ੿ࠂೞ੗.
34. X1 X784 W1 W784 W1X1 + … + W784X784 = Y Yо ௼ݶ ೙ӝ୓о 5ۄח ڷ.
35. - W1X1 + … + W784X784 = Y - X1ࠗఠ X784ө૑ ੓֎ਃ? ੑ۱੉ 784ѐ - W1ࠗఠ W784ө૑ ੓֎ਃ? о઺஖о 784ѐ - ইۄ࠺ই ं੗о 0ࠗఠ 9ө૑ਗ਼ইਃ? о઺஖о 7840ѐ (784 x 10) न҃ݎ
36. X1 X2 Y1 W1 W2 X784 … Y2 Y10 … 784ѐ ੑ۱ 0ੋоਃ? 1ੋоਃ? 9ੋоਃ? ୐ߣ૩ ೗ࣄ W10 W7840 7840ѐ о઺஖ 10ѐ ୹۱
37. X1 X2 Y1 X784 … Y2 Y10 … ੑ۱க ୹۱க
38. ؀୓ о઺஖ח 
 ־о ଻਋աਃ?
39. - ӝ҅о ҕࠗೞӝ ٸޙী ӝ҅ ೟ण - ӝ҅о ҕࠗೡ ࣻ ੓ѱ ޙઁ৬ ੿׹ਸ ળ࠺೤פ׮. - MNISTۄח ೙ӝ୓ ࣁ౟ب ੉޷૑৬ ੿׹੉ э੉ ઓ੤೤פ׮. - ف ઙܨ੄ ؘ੉ఠܳ ৮੹൤ ܻ࠙ೡ ӝ਎ӝ৬ ੺ಞਸ 
 ӝ҅о ଺ইմ׮Ҋ ࠁݶ ؾפ׮. - ೟ण ؘ੉ఠܳ о૑Ҋ ࣻ হ੉ ޷࠙ਸ ߈ࠂ ೞݴ о઺஖ܳ ઑӘঀ 
 Ҋ୛оݴ ৢ߄ܲ ݽ؛ਸ ٜ݅যцפ׮. - ੿׹ਸ ઱Ҋ ೟णਸ दఃח Ѫਸ ૑ب ೟ण੉ۄҊ ೤פ׮. ӝ҅೟ण
41. - Ӓې೗ਸ ਤ೧ GPUח ࣻ হ੉ Ӓܿ੗৬ ࡄ੉ ై ৔ؼ ੉޷૑ܳ ҅࢑ೞҊ ژ ҅࢑೤פ׮. - GPU੄ ఌਗೡ ҅࢑ מ۱਷ ݠन۞׬җ ঐഐ ചತ ী ੸೤೤פ׮. - ߈ݶ GPUח ਬোೠ ౸ױਸ ޅ೤פ׮. - 1950֙ ࠗఠ োҳػ AIо ੜ উغ঻؍ ੉ਬ ઺ ೞ ա۽ ো࢑ מ۱ ࠗ઒੉ ੉ঠӝ ؽ. - 1970֙ AI ѹ਎ - 1980֙ AI ѹ਎ - 2012֙ীঠ AIо ࡄਸ ࠆ. ݠन۞׬ب GPUо ೤פ׮.
42. NVIDIA੄ ୡ؀ഋ GPU (2রо۝)
43. GOOGLE੄ ݠन۞׬ ੹ਊ ஝ TPU (TENSOR PROCESSING UNIT)
44. ੿׹਷ ־о ੸աਃ?
47. ࠙ܨ ޙઁܳ ೐۽Ӓې߁ ਵ۽ ೧Ѿೡ ࣻ হաਃ?
49. - ೦࢚ ৘৻о ੓ਸ ࣻ ੓णפ׮. (Ҋন੉৬ ъই૑ ࠙ܨب ೐۽Ӓې߁੉ য۰਑) - ੋр੄ ঱যח ݽഐೞҊ ਋ܻо ਗೞח Ѿҗܳ ঳ӝ য۰਎ ࣻ ੓णפ׮. - ৘৻о ࢤѹب ৘৻੸ੋ ؘ੉ఠب ӝ҅ ೟णਸ दఃݶ ೧Ѿؾפ׮. - ݠन ۞׬਷ ѾҴ ਋ܻо ૒ҙਵ۽ ׮ܖ؍ ࠗ࠙ਸ ೧Ѿ೧ સפ׮. ૒ҙ਷ ঌҊ્ܻਵ۽ ಽӝ য۵णפ׮
50. - য়ܲଃ੄ ޙઁח ࢶਸ Ӓযࢲ ޙઁܳ ೧Ѿೡ ࣻ হ਺. - ࠂ੟ೠ ޙઁח ׮க੄ ۨ੉যо ೙ਃ. ੑ۱கҗ ୹۱கਵ۽ח উغח ޙઁ
51. X1 X2 X784 … … ੑ۱க Y1 Y2 Y10 … ୹۱க ਷ץக - ࠂ੟ೠ ޙઁח 1ѐ ੉࢚੄ ਷ץக(Hidden Layer)ਸ ٟ݅פ׮. - 2ѐ ੉࢚੄ ਷ץகਸ ೟णೞח ҃਋ Deep Learning੉ۄҊ ೞݴ बக न҃ݎ (Deep Neural Network)ۄח ݺடਸ ࢎਊ೤פ׮. - Microsoftח 152கਸ о૓ ResNetਸ ٜ݅׮ ੉റ 1001ѐ੄ கө૑ ٜ݅঻णפ׮.
52. MNIST पઁ ௏٘ ؘݽ
53. CNN
54. Ҋন੉ VS ѐ - बகݎਵ۽ח ੉޷૑ ࠙ܨ ޙઁܳ ੿ࠂೞӝ য۰ਛणפ׮. - CNN (Convolutional Neural Network)੄ AlexNet੉ աয়ݶࢲ ੉޷૑ ޙઁܳ ೧Ѿ. - 2012֙ 9ਘ 30ੌࠗఠ ஹೊఠо ૒ҙ੄ ৔৉ਸ ֈযࢲӝ द੘೮णפ׮.
55. 0 1 2 3 4 5 6 7 8 KERNEL੉ ೨ब ੑ۱ 0 1 2 3 ழօ 19 25 37 43 X = - 0 x 0 + 1 x 1 + 3 x 2 + 4 + 3 = 19 - “ழօ”਷ “੉޷૑ ೙ఠ”ۄҊ ࢤпೞݶ ؾפ׮. ੉޷૑ ೙ఠ۽ ؘ੉ఠܳ оҕೞח Ѫ. - ೙ఠ݃׮ ౠࢿਸ ъചೠ׮Ҋ ࢤпೞҊ ੓णפ׮. - যڃ ೙ఠח ਮҘਸ ъച? - যڃ ೙ఠח ӈա ௏ܳ ؊ ੜ ࠁ੉ѱ ъച? э਷ ࢚࢝ՙܻ ғೞҊ ؊೤פ׮.
56. X1 X2 X784 … … ੑ۱க Y1 Y2 Y10 … ୹۱க ਷ץக ழօ 3ѐ ೙ఠ
57. CNNਸ ా೧ റࠁܳ ҳೞҊ ހప ஠ܳ۽ ౟ܻ ࢲ஖۽ ࣁࠗ੸ੋ ࣻܳ ੍णפ׮.
58. CNN पઁ ௏٘ ؘݽ
59. ъച೟ण ъച೟ण
61. 0ࠗఠ 8ө૑ ஢ਸ ࢚కۄҊ ࢤп೤द׮. ࢚ೞઝ਋ ઺ ೞաܳ Ҋܰח Ѫਸ ঘ࣌੉ۄҊ ࠁҊਃ.
62. ъച೟ण - ഒ੗ ೒ۨ੉ (Self Play)ܳ ೞݴ प۱ਸ ט۰х. - (࢚క, ঘ࣌, थಁ ৈࠗ)ܳ о૑Ҋ ೟ण, ੉റ ࢚కী ؀೧ ࣻ೯೧ঠ ೡ ঘ࣌ਸ ঌ۰ષ. - ঌ౵Ҋח झझ۽ ؊ ъ೧૗. (ࢎ੹ ೟णೠ ӝࠁח ੷੘ӂ ೧Ѿػ 16݅ ӝࠁ. ؀ࠗ࠙ അ؀ ೐۽о ইש.) - CNN (੿଼ݎ, о஖ݎ) + ހప ஠ܳ۽ ౟ܻ ࢲ஖ + ъച ೟ण - ঌ౵ ઁ۽ח ӝࠁ ೟णب ೞ૑ ঋҊ ъച ೟ण݅ਵ۽ ֎౟ਕ௼ܳ ҳ୷. X1 X2 X784 … … ࢚క Y1 Y2 Y10 … ঘ࣌ ਷ץக ழօ
63. MINIMAX۽ ೧ب ؾפ׮. ъച೟ण + न҃ݎ + ހప஠ܳ۽ ౟ܻ ࢲ஖۽ ٜ݅঻णפ׮. 
 ALPHAZEROی э਷ ߑधਵ۽ਃ.
64. ALPHA ZERO ௿ۿ ؘݽ
65. ੋҕ૑מ੄ ࢎਊ ৘ ܻ࠭ ಣо ߣ৉ӝ ੸؀੸ ࢤࢿ न҃ݎ ੗ਯ ઱೯ ର۝ GPT-3 न࠙ૐ ੋध ୁࠈ नਊಣоݽ؛
66. - “ঘ࣌੉ ഴܯೞҊ ࠺઱঴੉ ഴܯ೮णפ׮.” -> ଵ (୶ୌ) - “ցޖ ੘ਤ੸੉Ҋ ઴Ѣܻо ࡞೮णפ׮.” -> Ѣ૙ (࠺୶) - CNNਵ۽ ೟णदெ ࢜۽਍ ܻ࠭ী ؀೧ ୶ୌੋ૑ ࠺୶ੋ૑ ഛੋ. ܻ࠭ ಣо
67. - RNNਸ ࢎਊ. CNNҗ੄ ର੉੼਷ ਷ץக੄ ؘ੉ఠܳ ׮द ਷ץகਵ۽ (ӝর۱) - ҳӖ੉ न҃ݎ ӝ߈੄ ߣ৉ӝܳ ݅ٚ ੉റ ֎੉ߡ ౵౵Ҋ ١ ؀ࠗ࠙ न҃ݎਵ۽. - ҳӖ਷ ঱য ೟੗ܳ Ҋਊೞ૑ ঋח׮Ҋ ೣ. ߣ৉ӝ RNN Y X RNN I RNN LOVE RNN YOU RNN դ RNN օ RNN ࢎی೧
68. - GAN (Generative Adversarial Network) - ੉޷૑੄ ف ࢎۈ਷ ઓ੤ೞ૑ ঋ਷ ࢎۈ. ੸؀੸ ࢤࢿ न҃ݎ
69. CNNਸ ੉ਊ೧ࢲ о૞ ੉޷૑ܳ ٜ݅য ղח GENERATOR৬ о૞ ੉޷૑ܳ ౸ݺೞח DISCRIMINATORо ؀݀ೣ. थܫ 50%о ؼ ٸө૑ ߈ࠂೞݶ ੉޷૑о ࢤࢿ.
70. IMAGE COLORING & IMAGE NOISE REDUCTION
72. ੗ਯ ઱೯ ର۝
74. - openAIо ݅ٚ ੋҕ૑מ. - Generative Pre-trained Transformer 3 - ߣ৉җ ؀ച, ੘ޙ੉ оמ - ࠺૑ب ೟ण - “I love you so much”ী ؀೧ ׮਺ਵ۽ ೟ण. - I -> Love - I love -> you - I love you -> so - I love you so -> much GPT-3
75. GPT-2о ೠҴয ؘݽо ੓যࢲ ੋਊ. SKTо ݅ٚ KOGPT2
76. - न࠙ૐ ղਊ਷ ੋध. - о૞ न࠙ૐੋ૑ח Ѩૐ೧ঠೣ. - CNNਸ ੉ਊ. न࠙ૐ ੋध
77. - ࢚׸ਗ੉ ؀ച ࢸ҅. ୁࠈ ؀਽ റ पઁ ࢎۈ੉ ؀਽. - ୡӝ ୁࠈ਷ RNNਵ۽ ҳഅ - ௑బஎ, ೟ण, QA ౱ਵ۽ ؀਽. - ஠஠য়ח 89.7%, ஠஠য়ߛ௼ח 34.1% ࢚׸ ୁࠈਵ۽ ؀਽ ৮ܐ. - ੌ߈਷೯਷ 10% ੿بо ୁࠈ ؀਽. ୁࠈ
78. - ਬ੷੄ ੑ୹۱ ղ৉ਸ ࠙ࢳ೧ࢲ ੗زਵ۽ ੷Ә. ੷Әా ੗ز ݽਵӝ
79. - ৈ۞ Ҋё ؘ੉ఠܳ ੉ਊ೧ ݠन۞׬ਸ ੉ਊ. - नਊಣоܳ ా೧ ઺नਊ؀୹. नਊಣоݽഋ
80. хࢎ೤פ׮.