Upgrade to Pro — share decks privately, control downloads, hide ads and more …

ベンチャー企業で言葉を扱うロボットの研究開発をする @東京大学 電子情報学特論I

ベンチャー企業で言葉を扱うロボットの研究開発をする @東京大学 電子情報学特論I

Yuya Unno

April 09, 2018
Tweet

More Decks by Yuya Unno

Other Decks in Technology

Transcript

  1. 7UYN A; WX l -2008 93EB=FRH7QCKI= l 2008-2011 25%*G9@DZL l

    2011-2016 G'/&"1&.!. + l 2016- G'/&"$!0 l 7QCKI=?[>S !(#1 l ChainerCuPy OSS<: l ?[ ),#-1LO<: NLPJ84 1.1?[>S 2015, VM6 PT>S 7QCKI= 2017, VM6 2
  2. 3 l 41214410 324 5 4 41 FP l f

    C T TP UNCn F l a c A INC l e d : Preferred Networks (PFN)
  3. 9/52% 9/5. /7 2%  36 l ,1&5!#*=>< )-' l

    /5(*=(;+:$4036" 8 14    
  4. -#*(0 3 l ! /." B1 2) l B3 4#*

    +,  %  l $' 1&B4  -#*(  15
  5. "&#(  l ,D5A>03+=1  4<*8. l ?12JLIKB 2000)F l

    :/$!%'@   GE  19 "!7H ;C9-6 =1
  6. & 2013  %#,*  ' ()" +$ ! 

    22 A. Stomakhin, C. Schroeder, L. Chai, J. Teran, A. Selle A material point method for snow simulation. SIGGRAPH 2013
  7. .#,*! + )  "" $(&/  l 1990"-'0 l

    2000"WWW l 2010%SNS l   24
  8.   : Siri     26 https://www.apple.com/jp/ios/siri/

    http://v-assist.yahoo.co.jp/ https://www.nttdocomo.co.jp/service/information/shabette_concier/
  9. $.(*!06;+/#DG1/2 l ?N59 l 19701;'PC< OM  l IK@>OM3OM l

    LF59 l LF59%*(20001872Q4=  BE"-)C J l  $.,LFAPLF0& * $H: 27
  10. #*&' -49(,! HK2/2 l @=DFHK l RSS+% @=DF)+2000/C 6BLG 

    l .7OM;A l :RSQ  l :RSQ$'&2000/650P3<   >JOM  l E2SQ+$#?N1"- I8 28
  11. !&  l %#!  ! l   

    "$    l    30
  12. )?3<8/  BD7. l 2000&%6= l 4G @HWeb*F9( l 2005&SNS9(

    l "$! *F9( l 2010& %'0 l A;+- 52$#%'0 l 2015&" #EC l " ,1:>9( 31
  13.  : Pepper, , , Jibo, … 33 https://www.jibo.com/ https://robohon.com/special/

    http://www.takaratomy.co.jp/p roducts/omnibot/ohanas/ http://www.softbank.jp/robot/ consumer/products/
  14. 34

  15. 2010!. -%)' *  l 2011~12Siri10 l 2013  l

    2014~15Pepper" l 2016  API l 2017   )& 35 #%+ /( $,
  16. -    37 *$ %! #$ ,+ 

    )("  '&
  17. <.?D3B=) l ;I=)#=) l 59&:FC$E9  l /G"! 7+ l

    59',8 -K,   l >A(UIAR l 1*%62@  39 H0?DJ 4.
  18. +&# *0/,' l 2012 l $("-  &  l

    2013 l 1  / l 2014 l LSTM3.).  l 2015 l %$ l 2016 l 4   !2  45
  19. SZ9X[Y4#H= # l  2# %F"1 5? AE #<G7;E l

    ! O:# V&NDJ # &@U  $] \ #  l   $!E8'.+(*#Q P# l 3:CIVL@U-,)*>W# $RT8/  l AE06B#MK# 47
  20. 2 0 49 http://incompleteideas.net/RL-FAQ.html Q: I am doing RL with

    a backpropagation neural network and it doesn't work; what should I do? A: It is a common error to use a backpropagation neural network as the function approximator … F A F 10 Q
  21. /E l B *FKO!2A -S?MJ5 !U ) 9+.1 l &'"$TX!7[

    PNI4  GM0L:0?Q!\Y8C l RW6V HZ%(#;3 <>D=@,   52
  22. &.$#"   !4 l  (,+ l ?@:9 ;0DC

     l  (  ,+ l 2A &. l %* F87B&. l 6=3  &. l  ,+ l 51/<)   l >'  (,+-E 56
  23. 59

  24. 5'& "#3.2 l 15"1% GPGPU* / !   +

    l #CuPy,974GPGPU8 6( l #  +-0 )$   60
  25. # &6   l #  ,.*8 "5 

    l (4/+9)1-%03 $ 61 !7' '2 50/+
  26. " 01 #7%1100 62 l >9 l BD?;  

    @<  l 6F=A!" l )81  l "5 l '%3&   HG l (024$C0+/,E.* :- l 81 
  27. ,. 341   l 9,. l #  l

    $&%  l /+!) 7  l ,. l #   l 2( $& 86* l /+!) 5 '0 "- 63
  28. !  " l !     l

    !  # l   65
  29. 66

  30. 59'1  =/$59"  !:6@.  l 41><& l !%70<&

    l !,?-)#* l (2 8;'3+ 67
  31. PFI/PFN2   68   )& + OSS 

     $"-   -   $"- ,%.* Blog '(#!  #! TechTalk 01/ 
  32. /    l * 1#' l )-.0/ *%3

     +4 $(' l * 1#'1#' l "&,!*1#' 25  69
  33. ( %(  &"  l ( &"$  !.1

    l ,*'  &" +) 70 ( &" / #&"-
  34. ?D@ l B;.FI l ?D!7 )9    l

    5*08/D2:H-<C l 9536=!E2 l 5,C%' l +>$"&(#14 l AG%' 71
  35. ,2 l >) #&')5-96?   $ l "&!%'0(84: 

    *+3 l 7<./ ')./ =;1  ') 74
  36.     l 892 l 430 l https://www.preferred-

    networks.jp/en/news/internship2018summer 75