人工知能の基本問題：これまでとこれから

人工知能学会 第110回人工知能基本問題研究会(SIG-FPAI)
2019年9月24日(火)・25日(水)
カナモトホール(札幌市民ホール)・第 2 会議室

総説(Open Access)
瀧川一学, 人工知能基本問題研究会(FPAI). 人工知能, 2019 年 34 巻 5 号 p. 603-611. https://doi.org/10.11517/jjsai.34.5_603

Transcript

1. 110 (SIG-FPAI)
 2019 9 24-25 ( ) (AIP)
 iPS (WPI-ICReDD) ichigaku.takigawa@riken.jp Permalink : http://id.nii.ac.jp/1004/00010344/
2. Vol.34 No.5 (2019/9) !2 ಛूɿʮݚڀձ঺հʯ w ਓ޻஌ೳجຊ໰୊ݚڀձʢ'1"*ʣ
   w ஌ࣝϕʔεγεςϜݚڀձʢ,#4ʣ
   w ݴޠɾԻ੠ཧղͱର࿩ॲཧݚڀձʢ4-6%ʣ
   w ઌਐతֶशՊֶͱ޻ֶݚڀձʢ"-45ʣ
 w ࢢຽڞ૑஌ݚڀձʢ$$*ʣ
   w ܭଌΠϯϑΥϚςΟΫεݚڀձʢ.&*ʣ
   w ਎ମ஌ݚڀձʢ4,-ʣ
   w "*
   νϟϨϯδݚڀձʢ$IBMMFOHFʣ
   w ൚༻ਓ޻஌ೳݚڀձʢ"(*ʣ
   w ҩ༻ਓ޻஌ೳݚڀձʢ"*.&%ʣ
3. = ... !3 SIG-FPAI kashi_pong ( ) 1. 2. 3. 4. The Hard Thing about Hard Things 5. : 6. : 7. : 8. : 9. : 
 FAI/FPAI 
 FAI/FPAI ( 100 )
4. !4 AI ( ) https://jsai.ixsq.nii.ac.jp/ 
 
 (Permlink )
5. ( ) !5 10 (1995 2004) 7 (2005 2011) 7 (2012 2018) ( )
 " L1 " ( )
 ( ) 
 ( )
 + JST : ( ) (2019 ) AIP iPS 
 ( ) 

6. (SIG-FPAI) !6 https://sig-fpai.org
8. AI ( ) !8 1984 
 ( UUCP JUNET ) 1992 (ISP) 1993 NCSA Mosaic 1994 IP 1995 NTT Windows 95 1996 Yahoo! JAPAN 1999 ADSL 2 2000 Google amazon.co.jp 2001 Wikipedia ADSL Yahoo! BB ADSL 2003 2004 SNS (mixi Ameba GREE ) 2005 YouTube iTunes Music Store 2008 iPhone Facebook Twitter 2009 Google Android SIG FAI SIG FPAI 1987 2004 Web ...
 ( ) *+$"*
   
   5PLZP
   
   /BHPZB
   
   /BHPZB
9. 30 : Vol.5, No.1 (1990 1 ) !9 Permalink : http://id.nii.ac.jp/1004/00002672/
10. Vol.34 No.5 (2019/9) !10 ಛूɿʮݚڀձ঺հʯ w ਓ޻஌ೳجຊ໰୊ݚڀձʢ'1"*ʣ
    w ஌ࣝϕʔεγεςϜݚڀձʢ,#4ʣ
    w ݴޠɾԻ੠ཧղͱର࿩ॲཧݚڀձʢ4-6%ʣ
    w ઌਐతֶशՊֶͱ޻ֶݚڀձʢ"-45ʣ
 w ࢢຽڞ૑஌ݚڀձʢ$$*ʣ
    w ܭଌΠϯϑΥϚςΟΫεݚڀձʢ.&*ʣ
    w ਎ମ஌ݚڀձʢ4,-ʣ
    w "*
    νϟϨϯδݚڀձʢ$IBMMFOHFʣ
    w ൚༻ਓ޻஌ೳݚڀձʢ"(*ʣ
    w ҩ༻ਓ޻஌ೳݚڀձʢ"*.&%ʣ
12. !12 Vol.34 No.5 (2019 9 ) Permalink : http://id.nii.ac.jp/1004/00010296/ ΦʔϓϯΞΫηεͰ
    ୭Ͱ΋ಡΊ·͢ʂ https://sig-fpai.org
13. ... !13 SIG-FPAI kashi_pong ( ) 1. 2. 3. 4. The Hard Thing about Hard Things 5. : 6. : 7. : 8. : 9. : 
 FAI/FPAI 
 FAI/FPAI ( 100 )
15. 2019/02/25 14:44 !15 : 2019 9 2018 2016 30 2 3 
 2 28 xxxx :
16. 2019/03/07 9:38 !16 2 9 2019 

17. Vol.11 No.3 (1996 5 ) !17 (1994-1995 FAI4 ) (1992-1993 FAI3 ) Permalink : http://id.nii.ac.jp/1004/00004008/
18. !18 (1990-1991 FAI2 ) (1987-1989 FAI ) Vol.11 No.3 (1996 5 ) Permalink : http://id.nii.ac.jp/1004/00004008/
19. !19 Vol.7 No.1 (1992 1 ) Permalink : http://id.nii.ac.jp/1004/00003060/
20. ͍·ͷʮػցֶशʯͱ
 ͍ͩͿ༷ࢠ͕ҧ͏
    ࿦ཧ w ʮϓϩάϥϛϯάݴޠݚڀʯ
    w ࿦ཧϓϩάϥϛϯά
    w ੍໿ϓϩάϥϛϯά
    w ؼೲ࿦ཧϓϩάϥϛϯά *-1
    w આ໌ʹجֶͮ͘श
    w ड़ޠ࿦ཧͷֶश
    w ໋୊࿦ཧͷֶश
    w ྨਪ w ؼೲਪ࿦
    w จ๏ਪ࿦
    ݴޠͷؼೲֶश
    w ܭࢉ࿦తֶश
    
    w (PMEͷۃݶಉఆ
    
    w 1MPULJOͷ࠷খ൚Խ
    
    w "OHMVJOͷؼೲਪ࿦
    
    w "OHMVJOͷ࣭໰ֶश
    
    w 4IBQJSPͷϞσϧਪ࿦
    
    w 7BMJBOUͷ1"$ֶश
     '"*ʹ͓͚Δʮػցֶशʯ ܾఆ໦ 1SPHPM
21. !21 2019 !? Vol.9 No.6 (1994 11 ) Permalink : http://id.nii.ac.jp/1004/00003683/
22. !22 Vol.3 No.6 (1988 11 ) Permalink : http://id.nii.ac.jp/1004/00002442/
23. !23
    
    4 
 
 ... ஌ࣝ޻ֶΤΩεύʔτγεςϜͷ
    ʮ஌ࣝ֫ಘͷϘτϧωοΫʯ
    ͔Β஌ࣝൃݟɾσʔλϚΠχϯά΁ Vol.11 No.6 (1996 11 ) Permalink : http://id.nii.ac.jp/1004/00004121/
24. !24 ՊݚඅɾಛఆྖҬݚڀ
    "
    
 ʮ
    ڊେֶज़ࣾձ৘ใ͔Βͷ
 ஌ࣝൃݟʹؔ͢Δجૅݚڀ
    ʯ Vol.15 No.4 (2000 7 ) Permalink : http://id.nii.ac.jp/1004/00004986/
25. KDD: Knowledge Discovery in Databases !25 ࠃࡍձٞ,%%͸΋ͱ΋ͱ͸"""*ͷ෼ՊձXPSLTIPQͱͯ͠೥୅ʹ࢝·Δ
 ࠷ޙͷ%Ͱ͋ΔʮJO
    %BUBCBTFTʯ͸ɺେن໛σʔλϕʔεࣗମ͕ίϞσΟςΟԽͨ͠
 ͜Ζʹ͠ΕͬͱʮBOE
    %BUB
    .JOJOHʯʹมߋʁ
    ͳͥ,%%.͡Όͳ͍ͷʁͱ͍͏ΞϨ
26. !26 Vol.18 No.5 (2003 9 ) Permalink : http://id.nii.ac.jp/1004/00004121/
27. Bernoulli-RIKEN Symposium on Neural Networks and Learning !27 October 25 - 27, 2000 Ohkouchi Hall, RIKEN (The Institute of Physical and Chemical Research), Japan 1. Graphical Models and Statistical Methods • Steffen L. Lauritzen (Aalborg University) • Thomas S. Richardson (University of Warwick) • Lawrence Saul (AT&T Labs) • Martin Tanner (Northwestern University) 2. Combining Learners • Leo Breiman (University of California, Berkeley) • Jerome H. Friedman (Stanford University) • Peter Bartlett (Australian National University) • Yoram Singer (The Hebrew University) 3. Information Geometry and Statistical Physics • Shinto Eguchi (The Institute of Statistical Mathematics) • Shun-ichi Amari (RIKEN Brain Science Institute) • Manfred Opper (Aston University) • Magnus Rattray (University of Manchester) 4. VC Dimension and SVM • Vladimir Vapnik (AT&T Labs) • Michael Kearns (AT&T Labs) • Gabor Lugosi (Pompeu Fabra University) • Bernhard Schoelkopf (Microsoft Research Ltd.) ͪ͜ΒͷྲྀΕ
 /*14ք۾ ͸ *#*4ݚڀձ΁ ೥લޙ͸Ұੈ෩ᴆ ͨ͠χϡʔϥϧωοτ͕ 47.౳ͷΧʔωϧ๏ɺ 3BOEPN
    'PSFTU΍ #PPTUJOHͳͲͷΞϯα ϯϒϧ๏ɺ֊૚తͳϕΠ ζϞσϧͳͲʹҠ͍ͬͯ ͘λΠϛϯά
28. !28 
 1987 ( ) ... Empirical ( )
 
 
 empirical ... 

29. data driven !29 
 
 
 GAFA empiricism theory-driven 
 ( )
30. !30 
 
 α 
 
 ...
31. Theory-driven vs Data-driven !31 David Hand All models are wrong, but some are useful (George Box) Theory-driven models can be wrong But data-driven models cannot be wrong or right Data-driven are not trying to describe an underlying reality. so they could be poor or useless, but not wrong But are merely intended to be useful http://videolectures.net/kdd2018_hand_data_science/ ߨԋϏσΦ͸ԼهͰެ։
    ൃදͰ͸͍͢͝αϓϥΠζ͕
    ώϯτɿࢦࣔ๮
32. Here is a title text 32 With enough data, the numbers speak for themselves. Chris Anderson (2008) cf.
33. Q. (or ) !33 ... ... 
 (vs )

34. !34 or etc. (UAI; Uncertainty in AI) / ( ) (or ) vs αʔΧϜεΫϦϓγϣϯ
35. vs : !35 Chomsky-Norvig debate Rahimi-LuCun debate Leo Breiman "Two Cultures" [Biology] Genome Sciences / X-omics / Systems Biology 
 [Neuroscience] Connectomics/Whole-Brain Simulation
 "low input, high throughput, no output science." (Sydney Brenner) Gallistel and King 'Memory and the Computational Brain' David Marr 'Vision' David Hand George Box Henri Poincaré ) ( ) Description or Explanation? Simulation or Emulation? Reverse-engineering a highly complex system whose inner workings are largely a mystery. Associationism (Correlation vs Causation), Deterministic Unpredictability (Chaos) ) JSAI 2019 (Preferred Networks)
 

36. debate !36 Vol.3 No.6 (1988 11 ) Vol.2 No.4 (1987 12 )
37. Chomsky Norvig debate !37 Peter Norvig (Google) Noam Chomsky (MIT) • (Chomsky) σʔλ͔Βͷ౷ܭత༧ଌʹجͮ͘ݱࡏͷAIͰ͸Պֶ͕ఏڙ͢΂ ͖આ໌΍ಎ࡯΍ҰൠݪཧʹࢸΒͳ͍ͷͰ͸ͱ൷൑ • (Chomsky) EngineeringͷՁ஋͸෼͔Δ͠ཧղͰ͖ΔΜ͚ͩͲɺ΋ͱ΋ͱͷ scientific question͔Β཭Ε͍ͯͳ͍͔͍ʁʁ (ࢠڙͷݴޠ֫ಘetcʣ • (Norvig) Science͸ٕज़΍Factऩूͱڞʹ૑ΒΕΔͷͰ͸ɻFactͷղऍͱ͸ ֬཰తͳ΋ͷͰ͸ͳ͍͔ɻ(ݕࡧΤϯδϯɾԻ੠ೝࣝɾػց຋༁ɾQAͷ੒ޭ) Factͷऩू+౷ܭత༧ଌ(֬཰తͳػցֶश༧ଌ) vs ୈҰݪཧͷཱ֬?
 (ߦಈओٛݴޠֶ vs ੜ੒จ๏΍ϛχϚϦετϓϩάϥϜͷ࠶೩ͱ΋?).
38. ) !38 RNN(LSTM/GRU) CNN ... Google BERT OpenAI GPT-2 GLUE SOTA SQuAD SOTA CMU XLNet Microsoft MT-DNN 2018/10/18 2019/01/31 2019/02/14 2019/06/19 Google RNN CNN Attention Transformer !? 
 (Attentive )
39. ) Attention Context !39 Attention ( ) ... 
 (mixture modeling...) m X i=1 ↵ifi(x) <latexit sha1_base64="GtBCcjWksxUuedJZIIM2Dm3iIpM=">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</latexit> m X i=1 ↵i(x)fi(x) <latexit sha1_base64="4Gy7Jf+OdRdINqIV17gPixBjMOc=">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</latexit> 
 
 context (query,key,value)
 context /subtype ... 
 ( ) "Attention Weights" m X i=1 ↵(x, xi)yi <latexit sha1_base64="6oQffE9M1ggtw70AKTqwsC04aYA=">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</latexit> ↵(x, xi) = k(x, xi) P j k(x, xj) <latexit sha1_base64="Cxvb1+n8meXd4W05ht9FxTHPKHI=">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</latexit> query key value ( )
 ? ࢀߟ) Attention Models in Graphs: A Survey (2018, arXiv:1807.07984)
40. ) ICML2019 Attention Tutorial !40 ଞͷྫ • DeepSets • Squeeze Excitation Networks (SENet) • Graph Attention Networks (GAT)
 : ⇢ X x (x) ! <latexit sha1_base64="k27i806uRdzJQ+/CLPr3hnr/HVA=">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</latexit> 1PPMJOH "UUFOUJPO
    1PPMJOH ⇢ X x ↵(x, w) (x) ! <latexit sha1_base64="x/crYdSJAAjdjkYWFYaDN5qVZLM=">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</latexit>
41. Context-Thick...? Attention...? !41 Vol.10 No.3 (1995 5 ) Permalink : http://id.nii.ac.jp/1004/00003785/
42. Neural Abstract Machines & Program Induction (NAMPI) !42 • Differentiable Neural Computers / Neural Turing Machines (Graves+ 2014) • Memory Networks (Weston+ 2014) • Pointer Networks (Vinyals+ 2015) • Neural Stacks (Grefenstette+ 2015, Joulin+ 2015) • Hierarchical Attentive Memory (Andrychowicz+ 2016) • Neural Program Interpreters (Reed+ 2016) • Neural Programmer (Neelakantan+ 2016) • DeepCoder (Balog+ 2016) context (attention ) ... IUUQTVDMNSHJUIVCJPOBNQJ 09:00-09:30 Dawn Song: Deep Learning for Program synthesis: Lessons & Open Challenges 09:30-10:00 Armando Solar-Lezama: Program synthesis and ML join forces 10:30-11:00 Sumit Gulwani: Programming by Examples: Logical Reasoning meets Machine Learning 11:00-11:30 Brenden Lake: Program induction for building more human-like machine learning algorithms 11:30-12:00 Satinder Singh: Program Induction and Language: Two Vignettes 12:00-12:30 Oriol Vinyals: Generating Visual Programs with Agents 14:00-14:30 Rishabh Singh: Neural Meta Program Synthesis 14:30-15:00 Veselin Raychev: Interpretable Probabilistic Models for Code 15:00-15:30 Richard Evans: Differentiable Inductive Logic Programming ICML2018 Workshop on NAMPI
43. Differentiable Inductive Logic Programming Richard Evans, Ed Grefenstette @LittleBimble, @egrefen https://jair.org/index.php/jair/article/view/11172
44. Rahimi LeCun debate !44 Yann LeCun
 (Facebook/NYU) Ali Rahimi 
 (Google/MIT) • (Ali Rahimi) ࠓͷػցֶश͸ʮAlchemyʯʹͳͬͯ͠·ͬͯɺػೳ͢Δ͚Ͳ த਎ͷ࢓૊Έ͸ෳࡶͰΑ͘Θ͔Βͳ͍ɻࣾձͷج൫(electricityʹྫ͑ͯ)ʹͭ ͔͏ʹ͸·ͩෆ҆ͳٕज़ͳͷͰAlchemy͔ΒElectricityΛऔΓ໭ͦ͏ɻ • (LeCun) ٕज़͸͍ͭ΋ཧ࿦తͳཧղΑΓઌߦ͖ͯͨ͠ɺ·ͨγϯϓϧͳఆཧ ͱҰൠԽ͸͢͹Β͍͕ͦ͠Ε͕ͳ͍ର৅΋͋Γ͑Δ͸ͣ (ྲྀମΛྫʹ)ɻ
45. ) The Imposteriors NIPS2017 !45
46. Breiman "Two Cultures" in Statistical Modeling !46
47. vs : !47 Chomsky-Norvig debate Rahimi-LuCun debate Leo Breiman "Two Cultures" [Biology] Genome Sciences / X-omics / Systems Biology 
 [Neuroscience] Connectomics/Whole-Brain Simulation
 "low input, high throughput, no output science." (Sydney Brenner) Gallistel and King 'Memory and the Computational Brain' David Marr 'Vision' David Hand George Box Henri Poincaré ) ( ) Description or Explanation? Simulation or Emulation? Reverse-engineering a highly complex system whose inner workings are largely a mystery. Associationism (Correlation vs Causation), Deterministic Unpredictability (Chaos) ) JSAI 2019 (Preferred Networks)
 

48. !48 Permalink : http://id.nii.ac.jp/1004/00007983/
49. !49
50. !50
51. !51 
 = (ill-posed) = regular (under tting) (over tting) etc. Inductive Bias
52. Theory-driven vs Data-driven !52 Theory-driven Data-driven " " Blackbox ( AI) (NP ) ( ) ( ) Data-Driven ( ) 
 Data ML etc etc
53. ... !53 SIG-FPAI kashi_pong ( ) 1. 2. 3. 4. The Hard Thing about Hard Things 5. : 6. : 7. : 8. : 9. : 
 FAI/FPAI 
 FAI/FPAI ( 100 )
54. https://itakigawa.github.io/news.html https://www.slideshare.net/itakigawa/presentations (Permlink )