SLIDE 1
- - PowerPoint PPT Presentation
- - PowerPoint PPT Presentation
!,/&"012,)"'34,&"',%.'5$."6'7/62"88$%&' @ANU ML Workshop, Sept 23, 2011 !"#$%&'($"' )"#$%&*#$"+,%-*".-*,-' Obama @ Texas 9",)$:;'$%':<$8'6%)$%"'=6/).' Mar10
SLIDE 2
SLIDE 3
9",)$:;'$%':<$8'6%)$%"'=6/).'
- ne year of digital life
news broadcast ten channels, one year 1,300 GB, 1,830 hrs ~200 GB? Oct’09: 4 billion photos 6000+/minute ~ 500 TB Apr’09 : 15 billion photos +220 million/week ~ 1.5PB Mar’10 : 24 hrs/minute 10% of internet traffic ~ 12 PB/yr ??
> ?,%;'6:<"/'"#,4@)"8A'
B C%./$6.'D'37<6%"'E?,@':/,2"8' B ?6F$)"'@<6%"'2,))'/"26/.8' B C))'"%G$/6%4"%:,)'H",:-/"8'8"%8".'.,$);'6G"/'C-8:/,)$,I'
SLIDE 4
J-:)$%"' '
> !,/&"082,)"K'=<;I'
B !"88'@/6%"':6'6G"/L:I'M"N"/'&"%"/,)$O,P6%' B Q,:,'G8'$%:"))$&"%2"'
> 12,)$%&'-@',%'15?'2),88$L"/' > 7/62"88$%&'26%8$."/,P6%8' > Q,:,0$%:"%8$G"'@/62"88$%&'H/,4"=6/R'
B S,.66@'T',@@)$2,P6%8'
SLIDE 5
Q,:,'IU'76="/'
[Banko and Brill ACL 01]
Task: confusion set disambiguation
the winning approaches and intervals
SLIDE 6
V#,4@)"A'12"%"'W64@)"P6%' '
[Hays and Efros SIGGRAPH07]
“… initial experiments with the GIST descriptor on ten thousand images were very discouraging … however increasing the dataset to one million yielded a qualitative leap.”
SLIDE 7
?!'1;8:"48'
SLIDE 8
5$8-,)'W6%2"@:'Q":"2P6%'
Task: score each image independently w.r.t. a set of pre-defined visual concepts.
SLIDE 9
X."46Y'
Aggregated performance over 50 “core” visual categories [Xie et al’11]. Raw classifier tags (baseline) Normalized classifier tags Precision-calibrated tags Taxonomy-refined tags Number of tags per image Tagging Precision (%) 80% precision, @4 tags per image “ImageNet-1000”, KNN “Social 20” KNN-voting [Li, Snoek’09] “ImageNet-1000”, UIUC-NEC “ImageNet-1000”, libLin*
SLIDE 10
1-@@6/:'5"2:6/'?,2<$%"8'
SLIDE 11
> Z/,$%$%&' > Z"8P%&'
15?'[$%'?!'2),88\''
alpha_star = quadprog(diag(z)*y'*y*diag (z), -ones(1, Nf), zeros(1, Nf) … )
Q-,)'H6/4A'C']7' 4,:),F'26."A'
SLIDE 12
^<,:'<;@"/0@,/,4":"/8I'
76);'%64$%,)'."&/""'.I' <6='4-2<'4$802),88$L2,P6%I' =<,:'R"/%")I'
SLIDE 13
15?'S;@"/0@,/,4":"/'1")"2P6%'
SLIDE 14
S6=':6'8")"2P6%'W',%.'&,44,I'
XQ-,%'":',)*K'_"-/6264@-P%&'`aabY'
> 7"/H6/4,%2"'8-/H,2"'=*/*:'<;@"/0@,/,4":"/'<$&<);'%6%0/"&-),/' > c0H6).'2/6880G,)$.,P6%'8""4':6',@@/6#$4,:"':"8:'"//'="))*'
SLIDE 15
^<"/"K',%.'<6='4-2<':6'8",/2<I'
> !$F15?'E-$."' > <N@ADDF)6&*846),*6/&' > _6/4,)$O"';6-/'.,:,' > W"%:"/'&,44,',/6-%.' d-,%P)"'8:,:8'6H'$%G"/8"' .$8:,%2"'$%':<"'.,:,*' > 1",/2<'W'$%')6&'8@,2"*'
]A'=<,:'"G,)-,P6%'2/$:"/$,':6'8",/2<'6%I' ]A'=<,:e8':<"'"//6/'-@@"/'F6-%.'H6/')",G"06%"06-:'2/6880G,)$.,P6%I''
SLIDE 16
> Z/,$%$%&' > Z"8P%&' > 7,/,4":"/'8")"2P6%'
15?A'^<"/"'$8':<"'264@-:,P6%'F6N)"'%"2RI'
]7A'J[_f`\gJ[_fb\' J[_f`\'F/-:"0H6/2"' W,%'="'"G"%'8:6/"'c'H6/'),/&"'_I' "*&*'_Uh"i' C..8'-@'d-$2R);A'j'H6).'#'k'G,)-"8'6H'W'#'b'R"/%")':;@"8'#'j'@,/,4":"/'G,)-"8'l''
SLIDE 17
E7m'1@"".'-@'6H'c"/%")'W64@-:,P6%'
> Z/,$%$%&'8@"".-@'gha#''
B iaaa0.$4"%8$6%'$%@-:'.,:,' B m@':6'baaaT':/,$%$%&'$%8:,%2"8'
> Z"8P%&'8@"".-@'II'
B 1<6-).'F"'"G"%'46/"'
<N@ADD4R),F*$P*&/D@/6n"2:DE7m0!3M15?'
SLIDE 18
E7m0Z,$)6/".'15?'XW6N"/'":',)K'cQQ'`ahhY'
> c";'$.",8'
B !6,.T86)G"'=6/R$%&'8":' 6%'E7m'[8$O"'hi\' B W)-8:"/'6%'8@,/8$:;' @,N"/%8':6'$4@/6G"'3DJ' B h8:'6/."/'<"-/$8P28'H6/' 2<668$%&','=6/R$%&'8":'
<N@ADDo2*-2<$2,&6*".-Dg26N"/D@/6n"2:8D&:8G4'
SLIDE 19
715?'XW<,%&'":*',)*'_371eapY'
> c";'$.",A'
B m8"'3Wq'[$%264@)":"'W<6)"8R;'q,2:6/$O,P6%\':6' ,@@/6#$4,:"'R"/%")'4,:/$#*' B 7"/H6/4'26)-4%0F,8".'3Wq',%.'.$8:/$F-:".'4,:/$#' 4-)P@)$2,P6%':6',2<$"G"'@,/,))")$O,P6%'
> gkh#'8@"".'-@'-8$%&'ja'4,2<$%"8'
B J%'`aac'$4,&"8'
code.google.com/p/psvm
SLIDE 20
22
random subspace bagging
[Yan, Tesic and Smith KDD07] Features Training Examples
SVM1 SVM2
Classifiers
SLIDE 21
23
Many approaches for scaling up
! Large number of models vs. large models ! Some applicable to other models (e.g. graph construction) ! Other issues: normalize input, imbalanced training data, normalize output?
…
N N n n
*
N N p p
[Chang et. al. NIPS’07] [Yan et. al. KDD’07]
Working set on GPU
SLIDE 22
J:<"/'@,/:8'6H':<"'?!'@$@")$%"'
SLIDE 23
V#,4@)"'r!,/&"s'7/62"88$%&'Z,8R8'
> Z,8R'hA'7CWC!'5JW'W<,))"%&"'`aha'
B `a':,/&":'2),88"8' B haKhab':/,$%$%&'$4,&"8K'`bcT'6Fn"2:8'
> Z,8R'`A'_31Z'Z9VW'?-)P4".$,'VG"%:'Q":"2P6%' [?VQ\'M"%2<4,/R'
B hj'"G"%:8' B hbKaaaT':/,$%$%&'G$."68K'b`KaaaT':"8P%&' 8,4@)".'G$."6'H/,4"8A'iiacT':/,$%$%&K'g`?':"8P%&''
SLIDE 24
W6)6/'S$8:6&/,4'
! M6o2"))$K'.,'5$%2$K'?6%":K'6/'?$/6I'
SLIDE 25
5$8-,)'^6/.8'H6/'34,&"'9":/$"G,)'
> 562,F-),/;'8$O"'hc'g'h?' > !62,)'.":"2:6/8'
B Q6EK'S"88$,%0Ct%"K'S,//$80Ct%"K' ?1V9K'S,//$80W6/%"/K'":2*'
> !62,)'."82/$@:6/8'
B 13qZK'7WC013qZK'E31ZK'1m9qK'":2*'
> Q$u"/"%:'26.$%&'4":<6.8'
B c04",%8K'<,8<$%&K'8@,/8"'26.$%&K' ":2'
SLIDE 26
M,2R06H0:<"0V%G")6@'7),%%$%&'
> 1:6/"'/,='.,:,A'giaaEM'G$."68' > q",:-/"'"#:/,2P6%'["*&*'M6^\'
B M6^A'`'8"2'D'$4,&"'
> 5JW'A'gb'<6-/8v''?VQA'ia'W7m'.,;8'' > 1:6/$%&'/,='13qZ'H",:-/"8A'ghZM'H6/'?VQ':/,$%$%&'
B JFn"2:'H",:-/"8A'`a'8"28'D'$4,&"'H6/''`aaT'6Fn"2:8'**''
> wh';",/'W7m'P4"'l''b'46%:<8'6%','d-,.026/"'7W'
> !",/%'46.")'
B 1:6/"'h?'#'`c''.$48'$%'4,:),FA'hi*kEMx' B 15?'gh'4$%'@"/']7'y'zW5[j\'y'z'@,/,4'[`k\'
'"'`'<6-/8x'
SLIDE 27
> Z<"'&66.'%"=8'
B ?68:'6H':<"8"'264@-:,P6%'$8'.,:,0',%.':,8R0' @,//,)$O,F)"' B 1:6/"'$%:"/4".$,:"'/"8-):8' B 4,%;'84,))'L)"8'<,/4H-)'[x\'
> r:,/'2HOsv'<,8<$%&'<")@8''
> ^<,:'$H'l'
B 7W'.$"8I' B 76="/'6-:,&"I' B _":=6/R'P4"6-:I''
r4,2<$%"')",/%$%&s'"'
SLIDE 28
HBase MapReduce Core Avro HDFS
Zoo Keeper
Hive Pig Chukwa
SLIDE 29
SLIDE 30
?,@9".-2"'
SLIDE 31
q,2"F66R'"#,4@)"A'2<"2R0$%'P4"8'
<N@ADD===*H,2"F66R*264D%6:"8DH,2"F66R0"%&$%""/$%&D$%:"/%$%&0,:0H,2"F66R0=<60 &6"80=<"/"0=<"%0,%.0=<;0$:04,N"/8Dhahja`{`i{h|i{|`a'
SLIDE 32
1-44,/;'
> !,/&"'.,:,'$8':<"':/"%.' > ?!',)&6/$:<48'"'@/,2P2"'' > C@@)$2,P6%08@"2$L2'@),%%$%&'$8'$4@6/:,%:' > ?,%;'@,/,))")'264@-P%&'@,/,.$&48':6'<")@'' > 6:<"/':6@$28'l'
B !,/&"',46-%:8'6H'8@,/8"'H",:-/"8' B E??K'W9q',%.'6:<"/'46.")8' B 3%G"/:".'$%."#K'<,8<$%&K'$%."#$%&'**''
SLIDE 33