Slide 1

Slide 1 text

%FFQ$POWPMVUJPOBM 7PJHIU,BNQGG5FTU -FT[FL3ZCJDLJ ϦϏπΩϨγΣοΫ

Slide 2

Slide 2 text

"CPVUNF • Born in Torun, Poland

Slide 3

Slide 3 text

"CPVUNF • Born in Torun, Poland • In ML since ~Y2K • 2011-2015 web dev. • 2016~ Cookpad

Slide 4

Slide 4 text

"CPVUNF • Born in Torun, Poland • In ML since ~Y2K • 2011-2015 web dev. • 2016~ Cookpad • Sci-Fi nerd • github: @lunardog

Slide 5

Slide 5 text

#MBEF3VOOFS

Slide 6

Slide 6 text

ϒϨʔυɾϥϯφʔ

Slide 7

Slide 7 text

Blade Runner Directed by Ridley Scott Produced by Michael Deeley Screenplay by Hampton Fancher David Peoples Based on Do Androids Dream of Electric Sheep? by Philip K. Dick Starring Harrison Ford Rutger Hauer Sean Young Edward James Olmos Music by Vangelis Cinematography Jordan Cronenweth Distributed by Warner Bros. Release date June 25, 1982 Running time 117 minutes Country United States Budget $28 million Box office $33.8 million Rachel Deckard

Slide 8

Slide 8 text

Rachel Replicant (bio-android) model Nexus 6

Slide 9

Slide 9 text

7PJHIU,BNQGG5FTU

Slide 10

Slide 10 text

5VSJOH5FTU

Slide 11

Slide 11 text

νϡʔϦϯάɾςετ

Slide 12

Slide 12 text

No content

Slide 13

Slide 13 text

5VSJOH5FTU

Slide 14

Slide 14 text

Was Deckard 
 a replicant?

Slide 15

Slide 15 text

5VSJOH5FTU Automated

Slide 16

Slide 16 text

5VSJOH5FTU Generative Adversarial Learning Generator Discriminator

Slide 17

Slide 17 text

%FFQ $POWPMVUJPOBM (FOFSBUJWF "EWFSTBSJBM /FUXPSLT

Slide 18

Slide 18 text

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks Alec Radford, Luke Metz, Soumith Chintala

Slide 19

Slide 19 text

Generator Discriminator Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks Alec Radford, Luke Metz, Soumith Chintala

Slide 20

Slide 20 text

No content

Slide 21

Slide 21 text

No content

Slide 22

Slide 22 text

8IBUFMTF ͦΕͰʁ

Slide 23

Slide 23 text

l&OIBODFz

Slide 24

Slide 24 text

*NBHF&OIBODJOH Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network Christian Ledig, Lucas Theis, Ferenc Huszar, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, Wenzhe Shi

Slide 25

Slide 25 text

%ˠ% Learning a Probabilistic Latent Space of Object Shapes via 3D Generative- Adversarial Modeling Jiajun Wu, Chengkai Zhang, Tianfan Xue, William T. Freeman, Joshua B. Tenenbaum

Slide 26

Slide 26 text

5FYUUP*NBHF Generative Adversarial Text to Image Synthesis Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele, Honglak Lee

Slide 27

Slide 27 text

"VUPNBUJD%SJWJOH

Slide 28

Slide 28 text

5IF&OE