Generative Adversarial Networks by Hasanov Vagif - TMLS #4

July 2016 (FOFSBUJWF"EWFSTBSJBM /FUXPSLT

Tokyo Machine Learning Society Presentation Reactive (FOFSBUFOBUVSBMMPPLJOHJNBHFT %PTFNJTVQFSWJTFEMFBSOJOHXJUIGFXMBCFMT CVUNBOZVOMBCFMFETBNQMFT (FOFSBUFJNBHFTPGQMBOFTXJUICJSEMFHT
8IZ(FOFSBUJWF"EWFSTBSJBM/FUXPSLT

Tokyo Machine Learning Society Presentation Reactive 5JNFMJOFPGTFMFDUFE(FOFSBUJWF"EWFSTBSJBM/FUXPSLTSFTFBSDI

Tokyo Machine Learning Society Presentation Reactive (FOFSBUJWF"EWFSTBSJBM/FUXPSLT *BO(PPEGFMMPXFUBM
VQMPBEFEJO+VOF 5JNFMJOFPGTFMFDUFE(FOFSBUJWF"EWFSTBSJBM/FUXPSLTSFTFBSDI

Tokyo Machine Learning Society Presentation Reactive 3BOEPN WFDUPS (FOFSBUPS NPEFM
3BOEPNTBNQMF GSPNUIFEBUBTFU %JTDSJNJOBUPS NPEFM QSPCBCJMJUZ QSPCBCJMJUZ JGSFBM JGHFOFSBUFE (FOFSBUPSJTUSZJOHUPNJOJNJ[FUIFNBYJNVNQPTTJCMF QFSGPSNBODFPGEJTDSJNJOBUPS (FOFSBUJWF"EWFSTBSJBM/FUXPSL

Tokyo Machine Learning Society Presentation Reactive JNBHFTPVSDFIUUQTQBQFSTOJQTDDQBQFSHFOFSBUJWFBEWFSTBSJBMOFUTQEG /PJTF %JTUSJCVUJPOPG SFBMEBUB
%JTUSJCVUJPOPG HFOFSBUFEEBUB %JTDSJNJOBUPS PVUQVU &YBNQMFGPSPOFEJNFOTJPOBMEBUB

Tokyo Machine Learning Society Presentation Reactive JNBHFTPVSDFIUUQTQBQFSTOJQTDDQBQFSHFOFSBUJWFBEWFSTBSJBMOFUTQEG (FOFSBUFEJNBHFT

VQMPBEFEJO+VOF %FFQHFOFSBUJWFJNBHFNPEFMTVTJOHB -BQMBDJBOQZSBNJEPGBEWFSTBSJBMOFUXPSLT &NJMZ%FOUPOFUBM VQMPBEFEJO+VOF 5JNFMJOFPGTFMFDUFE(FOFSBUJWF"EWFSTBSJBM/FUXPSLTSFTFBSDI

Tokyo Machine Learning Society Presentation Reactive #SFBLUIFDPNQMFYHFOFSBUPSGVODUJPOJOUPBTFSJFTPGMFTTDPNQMFY GVODUJPOT .BJOJEFB

Tokyo Machine Learning Society Presentation Reactive JNBHFTPVSDFIUUQBSYJWPSHQEGWQEG (FOFSBUFEEJ⒎FSFODF JNBHF "WFDUPSPGSBOEPN
OVNCFSTJO< > (FOFSBUPSOFUXPSL %JTDSJNJOBUPS OFUXPSL "DUVBMEJ⒎FSFODF JNBHF 5SBJOJOHUIFNPEFM

Tokyo Machine Learning Society Presentation Reactive JNBHFTPVSDFIUUQBSYJWPSHQEGWQEG 5SBJOJOHUIFNPEFM

Tokyo Machine Learning Society Presentation Reactive JNBHFTPVSDFIUUQXXXDTOZVFEVdEFOUPOQBQFSTMBQHBO@TVQQQEG

Tokyo Machine Learning Society Presentation Reactive JNBHFTPVSDFIUUQBSYJWPSHQEGWQEG (FOFSBUJOHJNBHFT

Tokyo Machine Learning Society Presentation Reactive JNBHFTPVSDF JNBHFqJQQFEIPSJ[POUBMMZ IUUQBSYJWPSHQEGWQEG $PBSTFUPpOFJNBHFHFOFSBUJPOQSPDFTT

Tokyo Machine Learning Society Presentation Reactive JNBHFTPVSDFIUUQXXXDTOZVFEVdEFOUPOQBQFSTMBQHBO@TMJEFTQEG (FOFSBUFEDIVSDIFT

VQMPBEFEJO+VOF %FFQHFOFSBUJWFJNBHFNPEFMTVTJOHB -BQMBDJBOQZSBNJEPGBEWFSTBSJBMOFUXPSLT &NJMZ%FOUPOFUBM VQMPBEFEJO+VOF 6OTVQFSWJTFESFQSFTFOUBUJPOMFBSOJOHXJUI EFFQDPOWPMVUJPOBMHFOFSBUJWFBEWFSTBSJBMOFUXPSLT "MFD3BEGPSEFUBM VQMPBEFEJO/PWFNCFS 5JNFMJOFPGTFMFDUFE(FOFSBUJWF"EWFSTBSJBM/FUXPSLTSFTFBSDI

Tokyo Machine Learning Society Presentation Reactive %FFQDPOWPMVUJPOBMHFOFSBUJWFBEWFSTBSJBMOFUXPSLT %$("/
("/XJUICFUUFSOFUXPSLBSDIJUFDUVSF

Tokyo Machine Learning Society Presentation Reactive 5SJDLT 3FQMBDFQPPMJOHXJUITUSJEFEDPOWPMVUJPOTJOEJTDSJNJOBUPS 6TFGSBDUJPOBMTUSJEFEDPOWPMVUJPOT EFDPOWPMVUJPOT
JOHFOFSBUPS JNBHFTPVSDFIUUQTBSYJWPSHQEGWQEG

Tokyo Machine Learning Society Presentation Reactive 5SJDLT 3FQMBDFQPPMJOHXJUITUSJEFEDPOWPMVUJPOTJOEJTDSJNJOBUPS 6TFGSBDUJPOBMTUSJEFEDPOWPMVUJPOT EFDPOWPMVUJPOT
JOHFOFSBUPS 6TFCBUDIOPSNBMJ[BUJPOJOCPUIUIFHFOFSBUPSBOEUIFEJTDSJNJOBUPS 3FNPWFGVMMZDPOOFDUFEIJEEFOMBZFSTGPSEFFQFSBSDIJUFDUVSFT 6TF3F-6BDUJWBUJPOJOHFOFSBUPSGPSBMMMBZFSTFYDFQUGPSUIFPVUQVU XIJDIVTFT5BOI 6TF-FBLZ3F-6BDUJWBUJPOJOUIFEJTDSJNJOBUPSGPSBMMMBZFST 6TF"%".PQUJNJ[BUJPONFUIPEGPSPQUJNJ[BUJPO BOEUXFBLUIF IZQFSQBSBNFUFST

Tokyo Machine Learning Society Presentation Reactive JNBHFTPVSDFIUUQTBSYJWPSHQEGWQEG (FOFSBUFECFESPPNJNBHFT

Tokyo Machine Learning Society Presentation Reactive .PSFJNBHFT JNBHFTPVSDFIUUQTBSYJWPSHQEGWQEG

Tokyo Machine Learning Society Presentation Reactive .PSFJNBHFT 0VSGSJFOE JNBHFTPVSDFIUUQTBSYJWPSHQEGWQEG

Tokyo Machine Learning Society Presentation Reactive JNBHFTPVSDFIUUQTBSYJWPSHQEGWQEG "SJUINFUJDTXJUIWFDUPST

VQMPBEFEJO+VOF %FFQHFOFSBUJWFJNBHFNPEFMTVTJOHB -BQMBDJBOQZSBNJEPGBEWFSTBSJBMOFUXPSLT &NJMZ%FOUPOFUBM VQMPBEFEJO+VOF 6OTVQFSWJTFESFQSFTFOUBUJPOMFBSOJOHXJUI EFFQDPOWPMVUJPOBMHFOFSBUJWFBEWFSTBSJBMOFUXPSLT "MFD3BEGPSEFUBM VQMPBEFEJO/PWFNCFS *NQSPWFE5FDIOJRVFTGPS5SBJOJOH("/T 5JN4BMJNBOTFUBM 6QMPBEFE+VOF 5JNFMJOFPGTFMFDUFE(FOFSBUJWF"EWFSTBSJBM/FUXPSLTSFTFBSDI

Tokyo Machine Learning Society Presentation Reactive .PSFUSJDLTGPSUSBJOJOH("/T 'FBUVSFNBUDIJOH (FOFSBUPSPCKFDUJWF

Tokyo Machine Learning Society Presentation Reactive .PSFUSJDLTGPSUSBJOJOH("/T 'FBUVSFNBUDIJOH .JOJCBUDIEJTDSJNJOBUJPOQBTTUIFJOGPSNBUJPOBCPVUUIFTJNJMBSJUZ CFUXFFOTBNQMFTXJUIJONJOJCBUDIUPUIFEJTDSJNJOBUPSOFUXPSL

Tokyo Machine Learning Society Presentation Reactive .PSFUSJDLTGPSUSBJOJOH("/T 'FBUVSFNBUDIJOH .JOJCBUDIEJTDSJNJOBUJPO )JTUPSJDBMBWFSBHJOHQFOBMJ[FMBSHFTVEEFODIBOHFTJOUIF
QBSBNFUFSTCZBEEJOHUPUIFDPTUGVODUJPOPGCPUI %BOE(

Tokyo Machine Learning Society Presentation Reactive .PSFUSJDLTGPSUSBJOJOH("/T 'FBUVSFNBUDIJOH .JOJCBUDIEJTDSJNJOBUJPO )JTUPSJDBMBWFSBHJOH
0OFTJEFEMBCFMTNPPUIJOHSFQMBDFUIFIBSEMBCFMTCZTPGUFS MBCFMT

Tokyo Machine Learning Society Presentation Reactive .PSFUSJDLTGPSUSBJOJOH("/T 'FBUVSFNBUDIJOH .JOJCBUDIEJTDSJNJOBUJPO )JTUPSJDBMBWFSBHJOH
0OFTJEFEMBCFMTNPPUIJOH 7JSUVBMCBUDIOPSNBMJ[BUJPOVTFBpYFESFGFSFODFCBUDIGPSUIF CBUDIOPSNBMJ[BUJPOTUBUJTUJDTDBMDVMBUJPO5IJTQSFWFOUTUIFOFUXPSL PVUQVUGPSBHJWFOTBNQMFCFJOHEFQFOEFOUPOUIFPUIFSTBNQMFT XJUIJONJOJCBUDI

Tokyo Machine Learning Society Presentation Reactive (FOFSBUFETNBMMJNBHFTBSFPGHPPERVBMJUZ JNBHFTPVSDFIUUQTBSYJWPSHQEGWQEG

Tokyo Machine Learning Society Presentation Reactive JNBHFTPVSDFIUUQTBSYJWPSHQEGWQEG 3FBMIPSTF 3FBMDBS (FOFSBUFETNBMMJNBHFTBSFPGHPPERVBMJUZ

Tokyo Machine Learning Society Presentation Reactive +VOF +VOF 1SPHSFTTPGUIFQBTUUXPZFBST "NB[JOH
JNBHFT`TPVSDFT IUUQTQBQFSTOJQTDDQBQFSHFOFSBUJWFBEWFSTBSJBMOFUTQEG IUUQTBSYJWPSHQEGWQEG

Tokyo Machine Learning Society Presentation Reactive %$("/ *NQSPWFE("/ -BSHFBOEDPNQMFYJNBHFHFOFSBUJPOJTTUJMMBOPQFOQSPCMFN JNBHFTPVSDFIUUQTBSYJWPSHQEGWQEG

Tokyo Machine Learning Society Presentation Reactive 4FNJTVQFSWJTFEMFBSOJOHXJUI("/T 6TFDMBTTJpFSBTBEJTDSJNJOBUPSCZBEEJOHBlHFOFSBUFEEBUBz ,
DMBTTUPJUTMJTUPGDMBTTFTGPSDMBTTJpDBUJPO 0QUJNJ[FTVQFSWJTFEBOEVOTVQFSWJTFEMPTTFTKPJOUMZ "DIJFWFTTUBUFPGUIFBSUGPSTFNJTVQFSWJTFEMFBSOJOHPO ./*45 $*'"3 47)/

Tokyo Machine Learning Society Presentation Reactive $PODMVTJPO 6TF("/TGPSHFOFSBUJOHTNBMMJNBHFT PSMBSHFCVUOPU DPNQMFYJNBHFT
6TF("/TUPUSBJODMBTTJpFSTXIFOZPVIBWFTNBMMBNPVOU PGMBCFMFEJNBHFT BOEMBSHFBNPVOUPGVOMBCFMFEJNBHFT

5IBOLZPV

Tokyo Machine Learning Society Presentation Reactive • Generative adversarial nets
  (Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio, NIPS, 2014) • Deep generative image models using a Laplacian pyramid of adversarial networks   (Emily Denton, Soumith Chintala, Arthur Szlam, Rob Fergus, NIPS, 2015) • Unsupervised representation learning with deep convolutional generative adversarial networks  (Alec Radford, Luke Metz, Soumith Chintala, ICLR, 2016) • Improved Techniques for Training GANs   (Tim Salimans, Ian J. Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, Xi Chen, arXiv: 1606.03498, 2016) 3FGFSFODFT

Generative Adversarial Networks by Hasanov Vagif - TMLS #4

Generative Adversarial Networks by Hasanov Vagif - TMLS #4

More Decks by Tokyo Machine Learning Society

Other Decks in Technology

Featured

Transcript