AI最新技術Update会 8月

イベント発表資料です。
https://deeplearning-b.connpass.com/event/181528/

Transcript

1. AI࠷৽ٕज़Updateձ 8݄ ᷂tech vein ழມ ॆԝ
2. ࣗݾ঺հ ழມ ॆԝ (͍ͷ·ͨ ΈͭͻΖ) גࣜձࣾ tech vein ୅දऔక໾ ݉ σϕϩούʔ twitter: @ino2222 IUUQTXXXUFDIWFJODPN
3. ΞδΣϯμ Archive Sanity (arxiv-sanity.com) ͔ΒϐοΫΞο ϓͨ͠ɺarxiv.org ͷաڈ1ϲ݄ؒͷ࿦จ঺հɻ ɾtop recentͷ࿦จτοϓ10 ɾtop hype ͷ࿦จτοϓ10 ɾҰ൪ؾʹͳͬͨ࿦จͷ঺հ
4. Archive Sanity? https://www.arxiv-sanity.com/top
5. Arxiv Sanity Top recent: Best10
6. ᶃTransfromer͸RNNͰ͢ɻઢܗ஫ҙͷߴ଎ࣗݾճؼτϥϯεϑΥʔϚʔ (ݪจ: Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention) Transformer͸͍͔ͭ͘ͷλεΫͰݦஶͳੑೳΛୡ੒͍ͯ͠Δ͕ɼ ೖྗͷ௕͞ʹରͯ͠ೋ࣍తͳෳࡶ͞Λ࣋ͭͨΊɼඇৗʹ௕͍γʔ έϯεͰ͸๏֎ʹ஗͍ɽ͜ͷ੍ݶʹରॲ͢ΔͨΊʹɼզʑ͸ࣗݾ ஫ҙΛΧʔωϧಛ௃ྔϚοϓͷઢܗ఺ੵͱͯ͠දݱ͠ɼߦྻੵͷ ࿈૝ੑͷੑ࣭Λར༻ͯ͠ɼෳࡶ͞Λ O(N^2) ͔Β O(N) ʹݮΒ͢ ͜ͱΛࢼΈΔɽ͜ͷఆࣜԽʹΑΓɺࣗݾճؼܕTransformerΛܶత ʹߴ଎Խ͠ɺϦΧϨϯτɾχϡʔϥϧɾωοτϫʔΫͱͷؔ܎Λ ໌Β͔ʹ͢Δ൓෮࣮૷͕ՄೳͰ͋Δ͜ͱΛࣔ͢ɻզʑͷઢܗม׵ ث͸όχϥม׵ثͱಉ༷ͷੑೳΛୡ੒͠ɺඇৗʹ௕͍γʔέϯε ͷࣗݾճؼత༧ଌʹ͓͍ͯ࠷େ4000ഒͷ଎౓Λୡ੒ͨ͠ɻ http://arxiv.org/abs/2006.16236v2
9. ᶄ ҟৗݕग़ͷͨΊͷσΟʔϓϥʔχϯά.ϨϏϡʔ (ݪจ: Deep Learning for Anomaly Detection: A Review) ҟৗ஋ݕग़ɺผ໊ʮ֎Ε஋ݕग़ʯ͸ɺ਺े೥લ͔Β༷ʑͳݚڀίϛϡχςΟ ʹ͓͍ͯɺӬଓతͰ͋Γͳ͕Β΋׆ൃͳݚڀ෼໺ͱͳ͍ͬͯ·͢ɻ·ͩ· ͩɺߴ౓ͳΞϓϩʔνΛඞཁͱ͢Δಠಛͷ໰୊ͷෳࡶ͞ͱ՝୊͕͋Γ· ͢ɻۙ೥ɺσΟʔϓϥʔχϯάΛར༻ͨ͠ҟৗ஋ݕग़ɺ͢ͳΘͪσΟʔϓ ҟৗ஋ݕग़͕ॏཁͳํ޲ੑͱͯ͠ු্͖͍ͯͯ͠Δɻຊ࿦จͰ͸ɺਂ૚ҟ ৗݕ஌ͷݚڀΛɺ3ͭͷߴϨϕϧΧςΰϦͱ11ͷࡉ෼ԽΧςΰϦʹ෼͚ͯ ໢ཏతͳλΫιϊϛΛ༻͍ͯϨϏϡʔ͢ΔɻຊߘͰ͸ɺ͜ΕΒͷख๏ͷओ ཁͳ௚؍ɺ໨తؔ਺ɺجૅͱͳΔԾఆɺ௕ॴͱ୹ॴΛϨϏϡʔ͠ɺલड़ͷ ՝୊ʹͲͷΑ͏ʹରॲ͍ͯ͠Δ͔Λٞ࿦͢Δɻ͞ΒʹɺকདྷͷՄೳੑͱ՝ ୊ʹରॲ͢ΔͨΊͷ৽ͨͳࢹ఺ʹ͍ͭͯ΋ٞ࿦͢Δɻ http://arxiv.org/abs/2007.02500v2
10. ܽؕݕग़ͷྫ (MVTec Adσʔληοτ) https://www.mvtec.com/company/research/datasets/mvtec-ad/
12. ᶅNVAE: ਂ૚֊૚తม෼ࣗಈΤϯίʔμʔ (ݪจ: NVAE: A Deep Hierarchical Variational Autoencoder) ਖ਼نԽϑϩʔɺࣗݾճؼϞσϧɺม෼ࣗಈΤϯίʔμʔʢVAEʣɺσΟʔϓΤωϧΪʔϕʔεϞ σϧ͸ɺσΟʔϓੜ੒ֶशͷͨΊͷڝ߹͢Δ໬౓ϕʔεͷϑϨʔϜϫʔΫͷҰͭͰ͋Δɻ͜Ε ΒͷதͰ͸ɺߴ଎Ͱѻ͍΍͍͢αϯϓϦϯάͱΞΫηε͠΍͍͢ූ߸ԽωοτϫʔΫͷར఺͕ ͋Δɻ͔͠͠ɺݱࡏͷͱ͜Ζɺਖ਼نԽϑϩʔ΍ࣗݾճؼϞσϧͷΑ͏ͳଞͷϞσϧʹ͸ྼͬͯ ͍ΔɻVAEͷݚڀͷେ෦෼͸౷ܭతͳ՝୊ʹয఺Λ౰͍ͯͯΔ͕ɺզʑ͸֊૚Խ͞ΕͨVAEͷ ͨΊͷχϡʔϥϧΞʔΩςΫνϟΛ৻ॏʹઃܭ͢Δͱ͍͏௚ަ͢Δํ޲ੑΛ୳Δɻզʑ͸ɺਂ ͞ํ޲ͷ෼཭Մೳͳ৞ΈࠐΈͱόονਖ਼نԽΛ༻͍ͯը૾ੜ੒ͷͨΊʹߏங͞Εͨਂ૚֊૚ܕ VAEͰ͋ΔNouveau VAEʢ̣̫̖̚ʣΛఏҊ͢ΔɻNVAE͸ਖ਼ن෼෍ͷ࢒ࠩύϥϝʔλԽΛඋ ͓͑ͯΓɺֶश͸εϖΫτϧਖ਼ଇԽʹΑͬͯ҆ఆԽ͞Ε͍ͯΔɻMNIST, CIFAR-10, CelebA HQ ͷσʔληοτʹ͓͍ͯɺNVAE͕ඇࣗݾճؼత໬౓ϞσϧͷதͰ࠷ઌ୺ͷ݁ՌΛୡ੒͠ɺ FFHQͷڧྗͳϕʔεϥΠϯΛఏڙ͢Δ͜ͱΛࣔ͢ɻྫ͑͹ɺCIFAR-10Ͱ͸ɺNVAE͸1࣍ݩ͋ ͨΓͷϏοτ਺Λ2.98͔Β2.91ʹԡ্͛͠ɺCelebA HQͰ͸ਤ1ʹࣔ͢Α͏ʹߴ඼࣭ͷը૾Λ ੜ੒͠·͢ɻࢲͨͪͷ஌ΔݶΓͰ͸ɺNVAE͸ɺ256x256ϐΫηϧͷେ͖͞ͷࣗવը૾ʹద༻ ͞Εͨ࠷ॳͷ੒ޭͨ͠VAEͰ͢ɻ http://arxiv.org/abs/2007.03898v1
13. ෮शɿVAE https://qiita.com/shionhonda/items/e2cf9fe93ae1034dd771
14. ෮श:VAE(2) • ಛ௃ZΛͣΒ͍ͯ͘͠ͱ݁Ռ͕มΘ͍ͬͯ͘
15. NVAEͷੜ੒ྫ
16. ˡͷS͸3FTJEVSBM
    /FUXPSL
    ˣ3FTJEVSBM
    /FUXPSLͷߏ଄
17. ᶆϞσϧϕʔεͷڧԽֶश.ௐࠪ (ݪจ: Model-based Reinforcement Learning: A Survey) ϚϧίϑܾఆϓϩηεʢMDPʣ࠷దԽͱͯ͠ҰൠతʹܗࣜԽ͞Ε͍ͯΔஞ࣍తҙࢥܾఆ ͸ɺਓ޻஌ೳͷॏཁͳ՝୊Ͱ͋Δɻ͜ͷ໰୊ʹର͢Δ2ͭͷॏཁͳΞϓϩʔν͸ɺڧԽֶ श(RL)ͱϓϥϯχϯάͰ͋ΔɻຊߘͰ͸ɺϞσϧϕʔεͷڧԽֶशͱͯ͠ΑΓΑ͘஌ΒΕ ͍ͯΔ྆෼໺ͷ౷߹ʹ͍ͭͯͷௐࠪΛ঺հ͢ΔɻϞσϧϕʔεRLʹ͸2ͭͷओཁͳεςο ϓ͕͋ΔɻୈҰʹɺ֬཰ੑɺෆ࣮֬ੑɺ෦෼తͳ؍ଌՄೳੑɺ࣌ؒతͳந৅ԽͳͲͷ՝୊ ΛؚΉྗֶϞσϧֶश΁ͷΞϓϩʔνΛମܥతʹѻ͏ɻୈೋʹɺܭըͱֶशͷ౷߹ͷମܥ తͳ෼ྨΛఏࣔ͠ɺͲ͔͜ΒܭըΛ։࢝͢Δ͔ɺܭըͱ࣮σʔλऩूʹͲͷΑ͏ͳ༧ࢉΛ ׂΓ౰ͯΔ͔ɺͲͷΑ͏ʹܭը͢Δ͔ɺֶशͱߦಈͷϧʔϓʹܭըΛͲͷΑ͏ʹ౷߹͢Δ ͔ɺͳͲͷଆ໘ΛؚΉɻ͜ΕΒ2ͭͷॏཁͳηΫγϣϯͷޙʹ͸ɺσʔλޮ཰ͷ޲্ɺ λʔήοτΛߜͬͨ୳ࡧɺ҆ఆੑͷ޲্ͳͲɺϞσϧϕʔεͷRLͷજࡏతͳར఺ʹ͍ͭͯ ΋ٞ࿦͢ΔɻௐࠪʹԊͬͯɺ֊૚తRL΍఻ୡͳͲͷؔ࿈͢ΔRL෼໺΍ɺߦಈ৺ཧֶͳͲͷ ଞͷݚڀ෼໺ͱͷؔ࿈ੑ΋͍ࣔͯ͠·͢ɻશମͱͯ͠ɺຊௐࠪͰ͸ɺMDP࠷దԽͷͨΊ ͷܭըֶशͷ૊Έ߹Θͤʹ͍ͭͯɺ෯޿͍֓೦తͳ֓ཁΛఏ͍ࣔͯ͠Δɻ http://arxiv.org/abs/2006.16712v2
18. ෮श:MDP(Ϛϧίϑܾఆաఔ) https://ja.wikipedia.org/wiki/%E3%83%9E%E3%83%AB%E3%82%B3%E3%83%95%E6%B1%BA%E5%AE%9A%E9%81%8E%E7%A8%8B 4ঢ়ଶ
    "ߦಈ
21. ᶇ χϡʔϥϧωοτϫʔΫͷάϥϑߏ଄ (ݪจ: Graph Structure of Neural Networks) χϡʔϥϧωοτϫʔΫ͸ɺχϡʔϩϯؒͷ઀ଓͷάϥϑͱͯ͠දݱ͞ΕΔ͜ͱ͕ ଟ͍ɻ͔͠͠ɺ޿͘࢖ΘΕ͍ͯΔʹ΋͔͔ΘΒͣɺχϡʔϥϧωοτϫʔΫͷάϥ ϑߏ଄ͱ༧ଌੑೳͱͷؔ܎ʹ͍ͭͯ͸ɺ΄ͱΜͲཧղ͞Ε͍ͯͳ͍ͷ͕ݱঢ়Ͱ͢ɻ ͜͜Ͱ͸ɺχϡʔϥϧωοτϫʔΫͷάϥϑߏ଄͕༧ଌੑೳʹͲͷΑ͏ͳӨڹΛ༩ ͑Δͷ͔Λܥ౷తʹௐ΂Δɻ͜ͷ໨తͷͨΊʹɺզʑ͸ؔ܎άϥϑͱݺ͹ΕΔ χϡʔϥϧωοτϫʔΫͷ৽͍͠άϥϑϕʔεͷදݱΛ։ൃͨ͠ɻ͜ͷදݱΛ༻͍ ͯɺҎԼͷ͜ͱΛࣔ͢ɻ(2)χϡʔϥϧωοτϫʔΫͷੑೳ͸ɺͦͷؔ܎άϥϑͷΫ ϥελϦϯά܎਺ͱฏۉύε௕ͷ׈Β͔ͳؔ਺Ͱ͋Δ͜ͱɺ(3)զʑͷ஌ݟ͸ଟ͘ͷ ҟͳΔλεΫ΍σʔληοτʹ͓͍ͯҰ؏͍ͯ͠Δ͜ͱɺ(4)εΠʔτεϙοτ͸ޮ ཰తʹಛఆͰ͖Δ͜ͱɺ(5)τοϓύϑΥʔϚϯεͷχϡʔϥϧωοτϫʔΫ͸ɺ࣮ ࡍͷੜ෺ֶతχϡʔϥϧωοτϫʔΫͷͦΕʹڻ͘΄Ͳࣅͨάϥϑߏ଄Λ͍࣋ͬͯ Δ͜ͱΛࣔ͢ɻզʑͷݚڀ͸ɺχϡʔϥϧΞʔΩςΫνϟͷઃܭͱχϡʔϥϧωο τϫʔΫҰൠͷཧղʹ৽ͨͳํ޲ੑΛ։͘΋ͷͰ͋Δɻ http://arxiv.org/abs/2007.06559v1
22. άϥϑߏ଄
24. ᶈ PyTorch3DʹΑΔ3DσΟʔϓϥʔχϯάͷߴ଎Խ (ݪจ: Accelerating 3D Deep Learning with PyTorch3D) http://arxiv.org/abs/2007.08501v1 ˒1JDL6Q
25. ᶉ ϥϕϧԽ͞Ε͍ͯͳ͍σʔλ͸͢΂ͯ౳͍͠Θ͚Ͱ͸ͳ͍ɻ൒ڭࢣ෇ֶ͖श ʹ͓͚ΔσʔλͷॏΈ෇ֶ͚श (ݪจ: Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning) طଘͷ൒ڭࢣ෇ֶ͖शʢSSLʣΞϧΰϦζϜ͸ɺϥϕϧ෇͖ྫͱϥϕϧ ͳ͠ྫͷଛࣦͷόϥϯεΛͱΔͨΊʹ୯ҰͷॏΈΛ࢖༻͍ͯ͠·͢ɺ͢ ͳΘͪɺ͢΂ͯͷϥϕϧͳ͠ྫ͕౳͘͠ॏΈ෇͚͞Ε͍ͯ·͢ɻ͔͠ ͠ɺϥϕϧ෇͚͞Ε͍ͯͳ͍σʔλ͕͢΂ͯ౳͘͠ͳΔΘ͚Ͱ͸ͳ ͍ɻ͜ͷ࿦จͰ͸ɺϥϕϧ෇͚͞Ε͍ͯͳ͍ྫ͝ͱʹҟͳΔॏΈΛ࢖ ༻͢Δํ๏Λݚڀ͍ͯ͠·͢ɻ͜Ε·ͰͷݚڀͰߦΘΕ͍ͯͨΑ͏ͳɺ ͢΂ͯͷॏΈΛखಈͰௐ੔͢Δ͜ͱ͸΋͸΍ෆՄೳͰ͋Δɻͦͷ୅Θ Γʹɺզʑ͸Өڹؔ਺ʹج͍ͮͨΞϧΰϦζϜΛ༻͍ͯॏΈΛௐ੔͢ Δɻ͜ͷΞϓϩʔνΛޮ཰తʹ͢ΔͨΊʹɺզʑ͸Өڹؔ਺ͷߴ଎Ͱ ޮՌతͳۙࣅΛఏҊ͢Δɻ͜ͷख๏͕ɺ൒ڭࢣ෇͖ը૾͓Αͼݴޠ෼ ྨλεΫʹ͓͍ͯɺ࠷ઌ୺ͷख๏ΑΓ΋༏Ε͍ͯΔ͜ͱΛ࣮ূ͢Δɻ http://arxiv.org/abs/2007.01293v1
26. ᶃ ᶄ ᶅ
27. ᶊϦΧϨϯτχϡʔϥϧωοτϫʔΫʹ͓͚Δτοϓμ΢ϯ৴߸ͱϘτϜΞοϓ ৴߸ͷ૊Έ߹ΘͤͷֶशͱϞδϡʔϧ্Ͱͷ஫ҙשى (ݪจ: Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural ݎ࿚ͳ஌֮͸ɺϘτϜΞοϓͱτοϓμ΢ϯͷ྆ํͷ৴߸ʹґଘ͍ͯ͠·͢ɻϘτϜΞοϓ ৴߸͸ɺײ֮Λ௨ͯ͠௚઀؍࡯͞ΕΔ΋ͷͰ͋Δɻτοϓμ΢ϯͷγάφϧ͸ɺաڈͷܦݧ ΍୹ظهԱʹجͮ͘৴೦΍ظ଴ɺྫ͑͹ʮϐʔφοπόλʔͱʙ...ʯͱ͍͏ϑϨʔζ͕Ͳͷ Α͏ʹ׬੒͢Δ͔ͱ͍͏Α͏ͳ΋ͷͰ͢ɻϘτϜΞοϓ৘ใͱτοϓμ΢ϯ৘ใͷ࠷దͳ૊ Έ߹Θͤ͸ະղܾͷ໰୊Ͱ͋Δ͕ɺͦͷ૊Έ߹Θͤํ͸ಈతͰ͋Γɺจ຺΍λεΫʹґଘ͠ ͍ͯͳ͚Ε͹ͳΒͳ͍ɻར༻Մೳͳજࡏతͳτοϓμ΢ϯ৘ใͷ๛෋͞ΛޮՌతʹར༻͠ɺ ૒ํ޲ΞʔΩςΫνϟͰͷ৴߸ͷࠞ͟Γ߹͍ͷෆڠ࿨ԻΛ๷͙ͨΊʹ͸ɺ৘ใͷྲྀΕΛ੍ݶ ͢ΔϝΧχζϜ͕ඞཁͰ͋Δɻզʑ͸ɺϘτϜΞοϓͱτοϓμ΢ϯͷ৴߸͕஫ҙΛ࢖ͬͯ ಈతʹ݁߹͞ΕΔσΟʔϓϦΧϨϯτχϡʔϥϧωοτΞʔΩςΫνϟΛ୳ٻ͍ͯ͠ΔɻΞʔ ΩςΫνϟͷϞδϡʔϧੑ͸ɺ৘ใͷڞ༗ͱ௨৴Λ͞Βʹ੍ݶ͢Δɻ஫ҙͱϞδϡʔϧੑ͸ ৘ใͷྲྀΕΛ༠ಋ͠ɺ஌֮ͱݴޠλεΫʹ͓͚Δ৴པੑͷߴ͍ੑೳ޲্Λ΋ͨΒ͠ɺಛʹ஫ ҙࢄອ΍ϊΠζͷଟ͍σʔλʹର͢ΔϩόετੑΛ޲্ͤ͞ΔɻຊݚڀͰ͸ɺݴޠϞσϦϯ άɺஞ࣍ը૾෼ྨɺϏσΦ༧ଌɺڧԽֶशͳͲͷ༷ʑͳϕϯνϚʔΫʹ͓͍ͯɺʮ૒ํ޲ੑʯ ৘ใͷྲྀΕ͕ڧྗͳϕʔεϥΠϯΑΓ΋݁ՌΛ޲্ͤ͞Δ͜ͱΛ࣮ূͨ͠ɻ http://arxiv.org/abs/2006.16981v1
28. Bidirectional Recurrent Independent Mechanisms (BRIMs)
29. 47(-14UPDIBTUJD
    7JEFP
    (FOFSBUJPO
    XJUI
    B
    -FBSOFE
    1SJPS
    IUUQTBSYJWPSHQEGQEG
31. ᶋ ϩόετੑͷଟ໘ੑɻ෼෍֎ҰൠԽͷ൷൑త෼ੳ (ݪจ: The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization) ຊݚڀͰ͸ɺը૾ελΠϧɺ஍ཧతҐஔɺΧϝϥૢ࡞ͳͲͷࣗવൃੜత ͳ෼෍มԽ͔ΒͳΔ3ͭͷ৽͍͠ϩόετੑϕϯνϚʔΫΛ঺հ͢Δɻ͜ ͷϕϯνϚʔΫΛ༻͍ͯɺҎલʹఏҊ͞Εͨ෼෍֎ϩόετੑʹؔ͢Δ ԾઆΛݕূ͠ɺͦΕΒΛݕূ͠·͢ɻ͜Ε·ͰͷݚڀͰͷओுʹ൓ͯ͠ɺ ΑΓେ͖ͳϞσϧͱ߹੒σʔλͷ૿ڧΛ࢖༻͢Δ͜ͱͰɺ࣮ੈքͷ෼෍ γϑτʹର͢Δϩόετੑ͕վળ͞ΕΔ͜ͱ͕Θ͔Γ·ͨ͠ɻ͜ΕΛ ͖͔͚ͬʹɺզʑ͸࠷ઌ୺ͷٕज़Λਐาͤ͞ɺ1000ഒҎ্ͷϥϕϧ෇͚ ͞ΕͨσʔλͰࣄલֶश͞ΕͨϞσϧΛ྇կ͢Δ৽͍͠σʔλ૿ڧ๏Λ ಋೖ͠·ͨ͠ɻͦͷ݁Ռɺ͍͔ͭ͘ͷख๏͸ςΫενϟ΍ہॴతͳը૾ ౷ܭʹ͓͚Δ෼෍ͷมԽʹ͸Ұ؏ͯ͠༗ޮͰ͋Δ͕ɺ஍ཧతมԽͷΑ͏ ͳଞͷ෼෍ͷมԽʹ͸༗ޮͰͳ͍͜ͱ͕Θ͔ͬͨɻࠓޙͷݚڀͰ͸ɺෳ ਺ͷ෼෍γϑτΛಉ࣌ʹݚڀ͠ͳ͚Ε͹ͳΒͳ͍ͱ݁࿦͚͍ͮͯ·͢ɻ http://arxiv.org/abs/2006.16241v1
32. ৽͍͠ϩόετωεࢦඪͷ঺հ
33. ImageNet-R ࣮෺͚ͩͰͳ͘૑࡞෺΋ؚΉ
34. • DeepFassion Remixed ద౰ͳΧϝϥઃఆʢζʔϜɾαΠζɾϑΥʔΧεͳ ͲʣͰࡱӨͨ͠ෳ਺ͷҥྉ඼ͷϚϧνϥϕϧ෼ྨλ εΫͷͨΊͷσʔληοτɻ • SVSF • ετϦʔτϏϡʔͷళͷ֎؍Λళฮͷۀछ͝ͱʹ ෼ྨͨ͠σʔλ(ඇެ։)
35. طଘ࿦จͷ7ͭͷϩόετੑԾઆͷݕূ(Ұ෦ൈਮ): ʮDiverse Data Augmentation͸ࣗવͳϩόετੑΛॿ͚ͳ͍આʯ DeepAugumentͨ͠σʔλͰݕূ → ImageNet-R͚ͩޮՌత
36. ᶌਆܦϓϩάϥϜʹ͓͚ΔڧྗͳҰൠԽͱޮ཰ੑ (ݪจ: Strong Generalization and Efficiency in Neural Programs) ຊݚڀͰ͸ɺχϡʔϥϧϓϩάϥϜ༠ಋͷ࿮૊ΈͷதͰɺڧྗʹҰൠԽ͢Δޮ཰త ͳΞϧΰϦζϜΛֶश͢Δ໰୊Λݚڀ͍ͯ͠·͢ɻχϡʔϥϧϞσϧͷೖग़ྗΠϯ λϑΣʔεΛ৻ॏʹઃܭ͠ɺ໛฿͢Δ͜ͱͰɺ೚ҙͷೖྗαΠζʹରͯ͠ਖ਼͍݁͠ ՌΛग़͢ϞσϧΛֶश͠ɺڧྗͳҰൠԽΛ࣮ݱ͢Δɻ·ͨɺڧԽֶशΛར༻͢Δ͜ ͱͰɺϓϩάϥϜͷޮ཰ࢦඪΛ࠷దԽ͠ɺ໛฿Ͱ࢖༻ͨ͠ڭࢣΛ௒͑Δ৽͍͠Ξϧ ΰϦζϜΛൃݟ͢Δ͜ͱ͕Ͱ͖Δɻ͜ΕʹΑΓɺզʑͷΞϓϩʔν͸ɺιʔτɺॱ ং෇͖ϦετͰͷݕࡧɺNP׬શͳ0/1φοϓβοΫ໰୊Ͱςετͨ͠Α͏ʹɺ༷ʑ ͳ໰୊ʹରͯ͠ΧελϜهड़͞ΕͨղΛ্ճΔੑೳΛֶश͢Δ͜ͱ͕Ͱ͖ɺχϡʔ ϥϧϓϩάϥϜ༠ಋͷ෼໺Ͱ஫໨͢΂͖ϚΠϧετʔϯΛઃఆ͍ͯ͠ΔɻϋΠϥΠ τͱͯ͠ɺզʑͷֶशϞσϧ͸ɺզʑ͕ςετͨ͠ͲͷΑ͏ͳೖྗσʔλαΠζͰ ΋ɺO(n log n)ͷෳࡶ͞ͰιʔτΛ׬ᘳʹ࣮ߦ͢Δ͜ͱ͕Ͱ͖ɺҰํͰɺֶशதʹ ݟΒΕͨϦεταΠζΛ͸Δ͔ʹ௒͑ΔϦεταΠζͰ΋ɺΫΠοΫιʔτΛؚΉ ϋϯυίʔυԽ͞ΕͨΞϧΰϦζϜΛૢ࡞ճ਺Ͱ্ճΔ͜ͱ͕Ͱ͖·ͨ͠ɻ http://arxiv.org/abs/2007.03629v2
37. a=f(s) ͷ f ΛҰൠԽֶͭͭ͠श͢Δ • ྫ) a=ιʔτ݁Ռσʔλɺs=ιʔτର৅σʔλ G
    T B ֶश
38. Arxiv Sanity Top hype: Best10
39. ᶃ GShard: ৚݅෇͖ܭࢉͱࣗಈγϟʔσΟϯάΛ༻͍ͨڊେϞσϧͷεέʔϦ ϯά (ݪจ: GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding) χϡʔϥϧωοτϫʔΫͷεέʔϦϯά͸ɺ๲େͳྔͷֶशσʔλͱܭࢉྔΛ࣋ͭଟ͘ ͷ࣮ੈքͷػցֶशΞϓϦέʔγϣϯʹ͓͍ͯɺϞσϧͷ඼࣭Λ޲্ͤ͞ΔͨΊʹॏཁ ͳ໾ׂΛՌ͖ͨͯ͠·ͨ͠ɻ͜ͷΑ͏ͳεέʔϦϯάͷ܏޲͸ɺϞσϧ඼࣭Λ޲্ͤ͞ ΔͨΊͷ࣮֬ͳΞϓϩʔνͰ͋Δ͜ͱ͕֬ೝ͞Ε͍ͯ·͕͢ɺͦͷಓͷΓʹ͸ɺܭࢉί ετɺϓϩάϥϛϯάͷ༰қ͞ɺฒྻσόΠε্Ͱͷޮ཰తͳ࣮૷ͳͲͷ՝୊͕͋Γ· ͢ɻGShard͸ɺܰྔͳΞϊςʔγϣϯAPIͱXLAίϯύΠϥͷ֦ுػೳ͔ΒͳΔϞ δϡʔϧͰ͢ɻGShard͸ɺطଘͷϞσϧίʔυΛ࠷খݶʹมߋ͢Δ͚ͩͰɺ෯޿͍ฒྻ ܭࢉύλʔϯΛදݱ͢ΔΤϨΨϯτͳํ๏Λఏڙ͠·͢ɻGShard͸ɺࣗಈγϟʔσΟϯ άΛ༻͍ͯɺεύʔεϦʔɾήʔςουɾϛοΫενϟʔɾΦϒɾΤΩεύʔτʹΑΔ ଟݴޠχϡʔϥϧػց຋༁τϥϯεϑΥʔϚʔϞσϧΛ6000ԯݸͷύϥϝʔλΛ௒͑ͯ εέʔϧΞοϓ͢Δ͜ͱΛՄೳʹ͠·ͨ͠ɻ͜ͷΑ͏ͳڊେͳϞσϧΛ2048TPU v3Ξ ΫηϥϨʔλ্Ͱ4೔ؒͰޮ཰తʹֶश͠ɺ100ݴޠ͔Βӳޠ΁ͷ຋༁ʹ͓͍ͯɺैདྷ ͷٕज़ͱൺֱͯ͠͸Δ͔ʹ༏Εͨ඼࣭Λୡ੒Ͱ͖Δ͜ͱΛ࣮ূ͠·ͨ͠ɻ http://arxiv.org/abs/2006.16668v1
40. ᶄᷖճతMCMCɿ౷ҰతͳϑϨʔϜϫʔΫ (ݪจ: Involutive MCMC: a Unifying Framework) Ϛϧίϑ࿈࠯ϞϯςΧϧϩ๏ʢMCMCʣ͸ɺਪ࿦ɺ౷߹ɺ࠷దԽɺγϛϡϨʔ γϣϯͳͲͷجຊతͳ໰୊ʹର͢ΔܭࢉΞϓϩʔνͰ͢ɻ͜ͷ෼໺Ͱ͸ɺ͞· ͟·ͳΞϧΰϦζϜ͕։ൃ͞Ε͓ͯΓɺͦͷಈػɺద༻ํ๏ɺαϯϓϦϯάͷ ޮ཰ੑͳͲ͕ҟͳΔɻ͢΂ͯͷҧ͍ʹ΋͔͔ΘΒͣɺͦΕΒͷଟ͘͸ಉ͡ίΞ ݪཧΛڞ༗͓ͯ͠Γɺզʑ͸ͦΕΛInvolutive MCMC (iMCMC)ϑϨʔϜϫʔ Ϋͱͯ͠౷Ұ͍ͯ͠·͢ɻ͜Εʹج͍ͮͯɺզʑ͸iMCMCͷ؍఺͔Β޿ൣғͷ MCMCΞϧΰϦζϜΛهड़͠ɺ৽͍͠MCMCΞϧΰϦζϜΛ։ൃ͢ΔͨΊͷઃ ܭݪཧͱͯ͠࢖༻Ͱ͖Δ͍͔ͭ͘ͷʮτϦοΫʯΛఆࣜԽ͢Δɻ͜ͷΑ͏ʹɺ iMCMC͸ଟ͘ͷط஌ͷMCMCΞϧΰϦζϜΛ౷ҰతʹݟΔ͜ͱ͕Ͱ͖ɺڧྗ ͳ֦ுػೳͷ։ൃΛ༰қʹ͠·͢ɻզʑ͸ɺط஌ͷՄٯMCMCΞϧΰϦζϜΛ ΑΓޮ཰తͳෆՄٯMCMCΞϧΰϦζϜʹม׵͢Δ2ͭͷྫΛ༻͍ͯɺޙऀΛ ࣮ূ͠·͢ɻ http://arxiv.org/abs/2006.16653v1
41. ෮शɿMCMC? • Ϛϧίϑ࿈࠯ • લͷঢ়ଶ͔Β࣍ͷঢ়ଶ͕ܾ·Δ • ϞϯςΧϧϩ๏ • ֬཰తΞϧΰϦζϜɻ • ϥϯμϜʹσʔλΛूΊͨΒɺਖ਼͍͠ॴʹσʔ λ͕ଟ͘ͳΔɻ
42. https://qiita.com/kenmatsu4/items/55e78cc7a5ae2756f9da
43. iMCMC ͰఆࣜԽ͞Εͨ Trickྫ σʔλ෼෍ೱ౓͕ೱ͍ʢ֬཰͕ߴ͍ʣͱ͜Ζ͔Βബ ͍ʢ௿͍ʣͱ͜Ζ΁ͷҠಈΛڋ൱͢Δ αϯϓϧιʔε: https://github.com/necludov/iMCMC
44. ᶅ ݴޠϞσϧ͸গ਺ਫ਼Ӷͷֶशऀ (ݪจ: Language Models are Few-Shot Learners) ࠷ۙͷݚڀͰ͸ɺେن໛ͳςΩετͷίʔύεͰࣄલֶशΛߦͬͨޙɺಛఆͷλεΫͰඍௐ੔Λߦ͏͜ͱͰɺ ଟ͘ͷNLPλεΫ΍ϕϯνϚʔΫͰେ͖ͳ੒Ռ͕ಘΒΕ͍ͯΔ͜ͱ͕࣮ূ͞Ε͍ͯΔɻΞʔΩςΫνϟతʹ͸ λεΫʹͱΒΘΕͳ͍ͷ͕ҰൠతͰ͕͢ɺ͜ͷํ๏Ͱ͸਺ઍ͔Β਺ສͷྫ୊ͷλεΫݻ༗ͷඍௐ੔σʔληο τ͕ඞཁͱͳΓ·͢ɻରরతʹɺਓؒ͸Ұൠతʹɺ৽͍͠ݴޠλεΫΛ਺ݸͷྫ΍؆୯ͳ໋ྩ͔Β࣮ߦ͢Δ͜ ͱ͕Ͱ͖·͕͢ɺ͜Ε͸ݱࡏͷNLPγεςϜͰ͸͍·ͩʹࠔ೉ͳ͜ͱͰ͢ɻ͜͜Ͱզʑ͸ɺݴޠϞσϧΛε έʔϧΞοϓ͢Δ͜ͱͰɺλεΫʹґଘ͠ͳ͍ɺ਺γϣοτͷੑೳΛେ෯ʹ޲্ͤ͞ɺ࣌ʹ͸ઌߦ͢Δ࠷ઌ୺ ͷඍௐ੔Ξϓϩʔνʹඖఢ͢Δੑೳʹୡ͢Δ͜ͱΛ͍ࣔͯ͠Δɻ۩ମతʹ͸ɺ1,750ԯݸͷύϥϝʔλΛ࣋ͭ ࣗݾճؼతݴޠϞσϧͰ͋ΔGPT-3Λֶशͤ͞ɺͦͷੑೳΛ਺γϣοτͷઃఆͰςετͨ͠ɻ͢΂ͯͷλεΫ ʹ͓͍ͯɺGPT-3͸ޯ഑ͷߋ৽΍ඍௐ੔ΛҰ੾ߦΘͣʹద༻͞ΕɺλεΫͱ਺γϣοτͷσϞ͸Ϟσϧͱͷς ΩετΠϯλϥΫγϣϯͷΈͰࢦఆ͞ΕͨɻGPT-3͸ɺ຋༁ɺ࣭໰Ԡ౴ɺΫϩʔδϯάͳͲͷଟ͘ͷNLPσʔ ληοτʹՃ͑ͯɺ୯ޠͷεΫϥϯϒϧղআɺจதͷ৽͍͠୯ޠͷ࢖༻ɺ3ܻͷԋࢉͳͲɺͦͷ৔Ͱͷਪ࿦΍ ྖҬదԠΛඞཁͱ͢Δ͍͔ͭ͘ͷλεΫʹ͓͍ͯ΋ߴ͍ੑೳΛୡ੒͍ͯ͠Δɻಉ࣌ʹɺGPT-3ͷ਺ൃֶश͕ະ ͩʹۤઓ͍ͯ͠Δσʔλ΍ɺେن໛ͳ΢Σϒίʔύε্Ͱͷֶशʹؔ࿈ͯ͠ํ๏࿦తͳ໰୊Λ๊͍͑ͯΔσʔ λΛ͍͔ͭ͘ڍ͛ͨɻ࠷ޙʹɺGPT-3͸ਓ͕ؒॻ͍ͨهࣄͱਓ͕ؒॻ͍ͨهࣄΛ۠ผ͢Δͷ͕೉͍͠χϡʔε هࣄͷαϯϓϧΛੜ੒͢Δ͜ͱ͕Ͱ͖Δ͜ͱΛൃݟͨ͠ɻຊݚڀͰ͸ɺ͜ͷൃݟͱGPT-3ͷҰൠతͳࣾձతӨ ڹʹ͍ͭͯٞ࿦͢Δɻ http://arxiv.org/abs/2005.14165v4 ઌ݄ɾઌʑ݄ͱॏෳ
45. ᶆઐ໳Ոͱͯ͠ͷࣄ࣮ɻ৅௃తͳ஌ࣝͷ্ʹదԠՄೳͰղऍՄೳͳਆܦه Ա (ݪจ: Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge) େن໛ͳݴޠϞσϧ͸ݱ୅ͷNLPϞσϦϯάͷத֩Ͱ͋Γɺ๲େͳྔͷৗ ࣝతͰࣄ࣮ʹج͍ͮͨ৘ใΛΤϯίʔυ͢Δ͜ͱ͕ࣔ͞Ε͍ͯ·͢ɻ͔͠ ͠ɺͦͷ஌ࣝ͸Ϟσϧͷજࡏతͳύϥϝʔλͷதʹ͔͠ଘࡏͤͣɺݕࠪ΍ ղऍʹΞΫηε͢Δ͜ͱ͸Ͱ͖·ͤΜɻ·ͨɺύϥϝʔλͱͯ͠อଘ͞Ε ͨ஌ࣝ͸ɺඞવతʹݪࢿྉʹ಺ࡏ͢Δ͢΂ͯͷόΠΞεΛࣔ͢͜ͱʹͳ Δɻ͜ΕΒͷ໰୊ʹରॲ͢ΔͨΊʹɺզʑ͸ɺه߸తʹղऍՄೳͳࣄ࣮৘ ใͱαϒγϯϘϧతͳਆܦ஌ࣝͱͷؒͷ໌ࣔతͳΠϯλʔϑΣʔεΛؚΉ ਆܦݴޠϞσϧΛ։ൃͨ͠ɻ͜ͷϞσϧ͕ɺ஌ࣝू໿తͳ2ͭͷ࣭໰Ԡ౴ λεΫͷύϑΥʔϚϯεΛܶతʹ޲্ͤ͞Δ͜ͱΛࣔ͢ɻ͞Βʹڵຯਂ͍ ͜ͱʹɺ͜ͷϞσϧ͸ɺͦͷه߸දݱΛૢ࡞͢Δ͜ͱͰɺ࠶܇࿅ͳ͠ʹߋ ৽͢Δ͜ͱ͕Ͱ͖Δɻಛʹ͜ͷϞσϧ͸ɺैདྷͷϞσϧͰ͸ෆՄೳͩͬͨ ৽͍͠ࣄ࣮ͷ௥Ճ΍طଘͷࣄ࣮ͷ্ॻ͖ΛՄೳʹ͢Δɻ http://arxiv.org/abs/2007.00849v1
46. Facts as Experts Ϟσϧߏ଄
47. ᶇFathomNet. ւ༸୳ࠪɾൃݟͷͨΊͷਫதը૾τϨʔχϯάσʔλϕʔε (ݪจ: FathomNet: An underwater image training database for ocean exploration and discovery) ԕִૢ࡞ंʢROVʣ΍ͦͷଞͷਫதࢿ࢈͔Β͸ɺ೥ؒ਺ઍ࣌ؒʹٴͿւ༸ϏσΦσʔλ͕ऩ ू͞Ε͍ͯ·͢ɻ͔͠͠ɺݱࡏͷख࡞ۀʹΑΔղੳํ๏Ͱ͸ɺROV΍େن໛ͳੜ෺ଟ༷ੑղ ੳͷͨΊͷϦΞϧλΠϜΞϧΰϦζϜͷͨΊʹऩूͨ͠σʔλΛे෼ʹ׆༻͢Δ͜ͱ͕Ͱ͖ ·ͤΜɻFathomNet͸ɺ࠷৽ͷΠϯςϦδΣϯτͰࣗಈԽ͞Εͨਫதը૾ղੳͷ։ൃΛՃ଎ ͢ΔͨΊʹ࠷దԽ͞Εͨɺ৽͍͠ϕʔεϥΠϯը૾τϨʔχϯάηοτͰ͢ɻࢲͨͪͷγʔ υσʔληοτ͸ɺ26,000࣌ؒҎ্ͷϏσΦςʔϓɺ680ສճͷΞϊςʔγϣϯɺ4,349ޠͷ ஌ࣝϕʔε͔ΒͳΔɺઐ໳ՈʹΑΔ஫ऍ෇͖ͷܧଓతͳσʔλϕʔε͔Βߏ੒͞Ε͍ͯ·͢ɻ FathomNet͸ɺ͜ͷσʔληοτΛ׆༻ͯ͠ɺػցֶशΞϧΰϦζϜͷ։ൃΛՄೳʹ͢Δͨ Ίʹɺਫதͷ֓೦ͷը૾ɺϩʔΧϦθʔγϣϯɺΫϥεϥϕϧΛఏڙ͍ͯ͠·͢ɻݱࡏ·Ͱ ʹɺதਫҬ΍ఈੜੜ෺ΛؚΉ233ͷҟͳΔΫϥεʹ͍ͭͯɺ80,000Ҏ্ͷը૾ͱ106,000Ҏ ্ͷϩʔΧϥΠθʔγϣϯ͕ఏڙ͞Ε͍ͯ·͢ɻզʑͷ࣮ݧͰ͸ɺऑڭࢣ෇͖ఆҐɺը૾ϥ ϕϦϯάɺ෺ମݕग़ɺ෼ྨͳͲͷΞϓϩʔνΛ༻͍ͯɺ༷ʑͳσΟʔϓϥʔχϯάΞϧΰϦζ ϜΛֶश͕ͤͨ͞ɺ͜ΕΒ͸༗๬Ͱ͋Δ͜ͱ͕Θ͔ͬͨɻ͜ͷ৽͍͠σʔληοτͰͷ༧ଌ ݁Ռ͸ྑ޷Ͱ͕͋ͬͨɺ࠷ऴతʹ͸ւ༸୳ࠪͷͨΊͷΑΓେ͖ͳσʔληοτ͕ඞཁͰ͋Δ ͜ͱΛ͍ࣔͯ͠Δɻ IUUQTBSYJWPSHBCTW
50. ᶈBlazePose.ΦϯσόΠεͰϦΞϧλΠϜʹମͷϙʔζΛτ ϥοΩϯά (ݪจ: BlazePose: On-device Real-time Body Pose tracking) զʑ͸ɺϞόΠϧσόΠε্ͰͷϦΞϧλΠϜਪ࿦ͷͨΊʹௐ੔͞Ε ͨɺਓؒͷϙʔζਪఆͷͨΊͷܰྔͳ৞ΈࠐΈχϡʔϥϧωοτϫʔ ΫΞʔΩςΫνϟͰ͋ΔBlazePoseΛ঺հ͠·͢ɻਪ࿦தɺ͜ͷωο τϫʔΫ͸Ұਓͷਓؒʹରͯ͠33ͷ਎ମΩʔϙΠϯτΛੜ੒͠ɺ Pixel 2ܞଳి࿩্Ͱຖඵ30ϑϨʔϜҎ্ͷ଎౓Ͱಈ࡞͠·͢ɻ͜ͷ ͨΊɺϑΟοτωετϥοΩϯά΍ख࿩ೝࣝͷΑ͏ͳϦΞϧλΠϜͷ Ϣʔεέʔεʹಛʹద͍ͯ͠·͢ɻզʑͷओͳߩݙ͸ɺ৽͍͠ମ੎τ ϥοΩϯάιϦϡʔγϣϯͱɺώʔτϚοϓͱΩʔϙΠϯτ࠲ඪ΁ͷ ճؼͷ྆ํΛ࢖༻͢Δܰྔͳମ੎ਪఆχϡʔϥϧωοτϫʔΫͰ͢ɻ http://arxiv.org/abs/2006.10204v1
53. طଘݚڀͱͷൺֱ BlazePose vs OpenPose
54. Ϟσϧߏ଄ʢখ͍͞ʂʣ
55. ᶉີͳςΩετݕࡧͷͨΊͷۙࣅ࠷ۙ๣ෛͷରরֶश (ݪจ: Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval) ֶश͞ΕͨີͳදݱۭؒΛ༻͍ͯςΩετݕࡧΛߦ͏͜ͱ͸ɺεύʔεݕࡧʹൺ΂ͯ ଟ͘ͷڵຯਂ͍ར఺͕͋Δɻ͔͠͠ɺີͳֶशදݱۭؒͰͷςΩετݕࡧͷ༗ޮੑΛ ߴΊΔͨΊʹ͸ɺεύʔεݕࡧͱͷ૊Έ߹Θ͕ͤඞཁͱͳΔ͜ͱ͕ଟ͍ɻຊ࿦จͰ ͸ɺֶशϝΧχζϜʹϘτϧωοΫ͕͋Δ͜ͱΛ໌Β͔ʹ͠ɺֶशʹ࢖༻͞ΕΔෛͷ Πϯελϯε͕ςετͰ͸ແؔ܎ͳจॻΛ୅ද͍ͯ͠ͳ͍͜ͱΛ໌Β͔ʹͨ͠ɻຊ࿦ จͰ͸ɺίʔύεͷۙࣅ࠷ۙ๣ʢANNʣΠϯσοΫε͔ΒωΨςΟϒΛߏங͠ɺֶ शϓϩηεͱฒߦͯ͠ߋ৽͢Δ͜ͱͰɺΑΓݱ࣮తͳωΨςΟϒֶशΠϯελϯεΛ બ୒͢ΔֶशϝΧχζϜͰ͋Δۙࣅ࠷ۙ๣ωΨςΟϒɾίϯτϥετਪఆʢANCEʣ ΛఏҊ͢Δɻ͜ΕʹΑΓɺDRͷֶशͱςετͰ࢖༻͞ΕΔσʔλ෼෍ͷෆҰக͕ࠜ ຊతʹղܾ͞ΕΔɻզʑͷ࣮ݧͰ͸ɺANCE͸BERT-Siamese DRϞσϧΛϒʔετ ͠ɺڝ߹͢Δີͳݕࡧͱૄͳݕࡧͷ͢΂ͯͷϕʔεϥΠϯΛ্ճΔੑೳΛࣔͨ͠ɻ ANCEͰֶशͨ͠දݱۭؒʹ͓͚ΔυοτϓϩμΫτΛ༻͍ͨεύʔεݕࡧ͓Αͼ BERT࠶ϥϯΩϯάͷਫ਼౓ͱ΄΅Ұக͠ɺ΄΅100ഒͷߴ଎ԽΛ࣮ݱͨ͠ɻ http://arxiv.org/abs/2007.00808v1
57. ᶊ޿͍ϕΠζχϡʔϥϧωοτϫʔΫͷਖ਼֬ͳࣄޙ෼෍ (ݪจ: Exact posterior distributions of wide Bayesian neural networks) ࠷ۙͷݚڀͰ͸ɺσΟʔϓϕΠδΞϯχϡʔϥϧωοτϫʔΫ(BNN)ʹΑͬ ͯ༠ى͞Εͨؔ਺ͷࣄલ෼෍͸ɺશ૚ͷ෯͕େ͖͘ͳΔʹͭΕͯΨ΢εա ఔ(GP)ͷΑ͏ʹৼΔ෣͏͜ͱ͕ࣔ͞Ε͍ͯΔɻ͔͠͠ɺଟ͘ͷBNNΞϓϦ έʔγϣϯͰ͸ɺBNNؔ਺ۭؒͷࣄޙॲཧ͕໰୊ͱͳ͍ͬͯ·͢ɻNeal (1996)΍MatthewsΒ(2018)ͷΦϦδφϧͷݚڀͰ͸ࣄޙऩଋͷ͍͔ͭ͘ͷ ܦݧతূڌ͕ఏڙ͞Ε͍ͯ·͕͢ɺͦΕ͸BNNࣄޙۙࣅͷਖ਼֬͞Λऔಘ͠ ͯݕূ͢Δ͜ͱͷѱ໊ߴ͍ࠔ೉͞ͷͨΊʹɺখ͞ͳσʔληοτ΍ΞʔΩ ςΫνϟʹݶఆ͞Ε͍ͯ·͢ɻզʑ͸ɺਖ਼֬ͳBNNࣄޙۙࣅ͕ɺࣄલ෼෍ ͷGPۃݶʹΑͬͯ༠ى͞ΕΔ΋ͷʹ(ऑ͘)ऩଋ͢Δͱ͍͏ܽམͨ͠ཧ࿦త ূ໌Λఏڙ͢Δɻ࣮ূతݕূͷͨΊʹɺখ͞ͳσʔληοτ্ͷ༗ݶBNN ͔ΒڋઈαϯϓϦϯάΛ༻͍ͯਖ਼֬ͳαϯϓϧΛੜ੒͢Δํ๏Λࣔ͢ɻ http://arxiv.org/abs/2006.10541v1
58. d͕େ͖͘ͳΔ΄Ͳແݶͷ෯ݶքͷࣄલॲཧͱಉ͡໬౓ͷࣄޙॲཧʹऩଋ͢Δ͜ͱΛূ໌͠ ͨɻແݶ෯ݶքࣄޙॲཧͷܭࢉ͕༰қͰ͋Ε͹ɺύϥϝʔλۭؒࣄޙॲཧͷධՁ͕ࠔ೉Ͱ͋ͬ ͯ΋ɺؔ਺ۭؒਪ࿦͕༰қʹͳΔಓ͕։͚Δɻ
59. ᶋֶश͞Εͨදݱͷઢܗࣝผੑʹ͍ͭͯ (ݪจ: On Linear Identifiability of Learned Representations) ࣝผՄೳੑ͸౷ܭϞσϧͷ๬·͍͠ಛੑͰ͋Γɺे෼ͳܭࢉࢿݯͱσʔλ͕ ͋Ε͹ɺਅͷϞσϧύϥϝʔλΛ೚ҙͷਫ਼౓ͰਪఆͰ͖Δ͜ͱΛҙຯ͠·͢ɻ զʑ͸දݱֶशͷจ຺ͰࣝผՄೳੑΛݚڀ͍ͯ͠·͢ɿԼྲྀͷλεΫʹؔͯ͠ ࠷దͳඇઢܗσʔλදݱΛൃݟ͢Δ͜ͱͰ͢ɻσΟʔϓχϡʔϥϧωοτϫʔ Ϋͱͯ͠ύϥϝʔλԽ͞Εͨ৔߹ɺͦͷΑ͏ͳදݱؔ਺͸ɺઃܭ্ύϥϝʔλ ͕ա৒ʹઃఆ͞Ε͍ͯΔͨΊɺҰൠతʹύϥϝʔλۭؒͰͷࣝผੑΛ͍͍ܽͯ ·͢ɻ͜ͷ࿦จͰ͸ɺ࠷ۙͷඇઢܗICAͷਐาʹج͍ͮͯɺେن໛ͳࣝผϞσ ϧͷϑΝϛϦʔ͕ɺઢܗෆ֬ఆੑ·Ͱؔ਺ۭؒͰ࣮ࡍʹࣝผՄೳͰ͋Δ͜ͱ Λࣔ͢͜ͱʹΑͬͯɺࣝผՄೳੑΛճ෮ͤ͞Δ͜ͱΛ໨తͱ͍ͯ͠Δɻදݱֶ शͷͨΊͷଟ͘ͷϞσϧ͸ɺςΩετɺը૾ɺԻ੠ͳͲɺ͞·͟·ͳྖҬͰ͜ ͷҙຯͰࣝผՄೳͰ͋Γɺൃද࣌ʹ͸࠷ઌ୺ͷ΋ͷͰͨ͠ɻզʑ͸ɺઢܗࣝ ผՄೳੑͷͨΊͷे෼ͳ৚݅Λಋग़͠ɺγϛϡϨʔτ͞Εͨσʔλͱ࣮ੈք ͷσʔλͷ྆ํͰ͜ͷ݁ՌΛ࣮ূతʹࢧ࣋͢Δɻ http://arxiv.org/abs/2007.00810v3
60. ࣝผՄೳੑʁ • ࣝผՄೳੑ͸౷ܭϞσϧͷ๬·͍͠ಛੑͰ͋ Γɺे෼ͳܭࢉࢿݯͱσʔλ͕͋Ε͹ɺਅͷ ϞσϧύϥϝʔλΛ೚ҙͷਫ਼౓ͰਪఆͰ͖Δ ͜ͱɻ
61. ࣝผՄೳੑΛٻΊΒΕΔϞσϧ ͷ৚݅(ಡ·ͳ͍͍ͯ͘Ͱ͢)
62. ࣝผՄೳੑΛٻΊΒΕΔͱخ͠ ͍͜ͱ • ֶशͨ͠࠷దͳදݱ͕࠶ݱ͠΍͍͔͢Ͳ͏͔Λ ༧ଌ͢Δͷʹ໾ཱͭˠ࠷దͳ݁ՌΛ࠶ݱ͢Δͷ ʹ(ݪଇͱͯ͠)̍౓ֶ͚ͩश͢Ε͹Α͘ͳΔɻ • ূ໌Մೳͳ࠷దͳ܇࿅ϞσϧϥΠϒϥϦʹஔ͖ ׵͑ΒΕΔΑ͏ʹͳΔɻ • ࣮ߦ͢ΔܭࢉϦιʔε͕ݮΔͷͰɺίετɾࢿ ݯͷ࡟ݮʹͳΔɻ
63. ᶌ ਆܦϓϩάϥϜʹ͓͚ΔڧྗͳҰൠԽͱޮ཰ੑ (ݪจ: Strong Generalization and Efficiency in Neural Programs) ຊݚڀͰ͸ɺχϡʔϥϧϓϩάϥϜ༠ಋͷ࿮૊ΈͷதͰɺڧྗʹҰൠԽ͢Δޮ཰త ͳΞϧΰϦζϜΛֶश͢Δ໰୊Λݚڀ͍ͯ͠·͢ɻχϡʔϥϧϞσϧͷೖग़ྗΠϯ λϑΣʔεΛ৻ॏʹઃܭ͠ɺ໛฿͢Δ͜ͱͰɺ೚ҙͷೖྗαΠζʹରͯ͠ਖ਼͍݁͠ ՌΛग़͢ϞσϧΛֶश͠ɺڧྗͳҰൠԽΛ࣮ݱ͢Δɻ·ͨɺڧԽֶशΛར༻͢Δ͜ ͱͰɺϓϩάϥϜͷޮ཰ࢦඪΛ࠷దԽ͠ɺ໛฿Ͱ࢖༻͢ΔڭࢣΛ௒͑Δ৽͍͠Ξϧ ΰϦζϜΛൃݟ͠·͢ɻ͜ΕʹΑΓɺզʑͷΞϓϩʔν͸ɺιʔτɺॱং෇͖Ϧε τͰͷݕࡧɺNP׬શͳ0/1φοϓβοΫ໰୊Ͱςετͨ͠Α͏ʹɺ༷ʑͳ໰୊ʹର ͯ͠ΧελϜهड़͞ΕͨղΛ্ճΔੑೳΛֶश͢Δ͜ͱ͕Ͱ͖ɺχϡʔϥϧϓϩά ϥϜ༠ಋͷ෼໺Ͱ஫໨͢΂͖ϚΠϧετʔϯΛઃఆ͍ͯ͠ΔɻϋΠϥΠτͱͯ͠ɺ զʑͷֶशϞσϧ͸ɺզʑ͕ςετͨ͠ͲͷΑ͏ͳೖྗσʔλαΠζͰ΋ɺ$O(n log n)$ͷෳࡶ͞ͰιʔτΛ׬ᘳʹ࣮ߦ͢Δ͜ͱ͕Ͱ͖ɺҰํͰɺֶशதʹݟΒΕͨ ϦεταΠζΛ͸Δ͔ʹ௒͑ΔϦεταΠζͰ΋ɺΫΠοΫιʔτΛؚΉϋϯυ ίʔυԽ͞ΕͨΞϧΰϦζϜΛૢ࡞ճ਺Ͱ্ճΔ͜ͱ͕Ͱ͖·ͨ͠ɻ http://arxiv.org/abs/2007.03629v2 5PQ
    SFDFOU
    /Pͱ ॏෳ
64. My favorite
65. ᶈ PyTorch3DʹΑΔ3DσΟʔϓϥʔχϯάͷߴ଎Խ (ݪจ: Accelerating 3D Deep Learning with PyTorch3D) σΟʔϓϥʔχϯά͸ɺ2Dͷը૾ೝࣝΛେ෯ʹվળ͖ͯͨ͠ɻ3Dʹ֦ு͢Δ͜ͱͰɺࣗ཯૸ߦंɺԾ૝ ݱ࣮΍֦ுݱ࣮ɺ3DίϯςϯπͷΦʔαϦϯάɺ͞Βʹ͸2DೝࣝͷվળͳͲɺଟ͘ͷ৽͍͠ΞϓϦέʔ γϣϯ͕ਐల͢ΔՄೳੑ͕͋Γ·͢ɻ͔͠͠ɺؔ৺͕ߴ·͍ͬͯΔʹ΋͔͔ΘΒͣɺ3DσΟʔϓϥʔχϯ ά͸·ͩൺֱతະ։୓ͳঢ়ଶʹ͋Γ·͢ɻ͜ͷΑ͏ͳ֨ࠩ͸ɺҟछσʔλͷޮ཰తͳॲཧ΍ɺάϥϑΟο Ϋεૢ࡞ΛࠩผԽ͢ΔͨΊͷϦϑϨʔϛϯάͳͲɺ3DσΟʔϓϥʔχϯάʹؔΘΔ޻ֶతͳ՝୊ʹىҼ ͍ͯ͠Δͱߟ͑ΒΕ͍ͯ·͢ɻզʑ͸ɺ3DσΟʔϓϥʔχϯάͷͨΊͷϞδϡʔϧԽ͞Εͨޮ཰తͰඍ෼ ՄೳͳԋࢉࢠͷϥΠϒϥϦͰ͋ΔPyTorch3DΛಋೖ͢Δ͜ͱͰɺ͜ΕΒͷ՝୊ʹରॲ͍ͯ͠·͢ɻ͜ͷϥ ΠϒϥϦʹ͸ɺϝογϡͱ఺܈ͷͨΊͷߴ଎ͰϞδϡʔϧࣜͷඍ෼ՄೳͳϨϯμϥʔؚ͕·Ε͓ͯΓɺ߹ ੒ʹΑΔղੳΞϓϩʔνΛՄೳʹ͍ͯ͠·͢ɻଞͷඍ෼ՄೳͳϨϯμϥʔͱൺֱͯ͠ɺPyTorch3D͸ΑΓ ϞδϡʔϧԽ͞Ε͓ͯΓɺޮ཰తͰ͋ΔͨΊɺϢʔβʔ͸ΑΓ؆୯ʹ֦ு͢Δ͜ͱ͕Ͱ͖ɺେ͖ͳϝο γϡ΍ը૾΁ͷεέʔϦϯά΋༰қͰ͢ɻPyTorch3D ͷԋࢉࢠͱϨϯμϥʔΛଞͷ࣮૷ͱൺֱ͠ɺ଎౓ͱ ϝϞϦͷେ෯ͳվળΛ࣮ূ͍ͯ͠·͢ɻ·ͨɺPyTorch3DΛ࢖༻ͯ͠ɺShapeNet্ͷ2Dը૾͔Βͷڭ ࢣͳ͠3Dϝογϡͱ఺܈༧ଌͷͨΊͷ࠷৽ٕज़Λվળ͠·ͨ͠ɻPyTorch3D͸ΦʔϓϯιʔεͰ͋Γɺ 3DσΟʔϓϥʔχϯάͷݚڀΛՃ଎ͤ͞ΔҰॿͱͳΔ͜ͱΛظ଴͍ͯ͠·͢ɻ http://arxiv.org/abs/2007.08501v1
66. 2Dը૾͔Βͷ3DγϧΤοτ༧૝
68. https://pytorch3d.org/
69. PyTorch3Dͷओཁͳػೳ • ࡾ֯ܗϝογϡͷอଘͱૢ࡞ͷͨΊͷσʔλ ߏ଄ • ࡾ֯ܗϝογϡͷޮ཰తͳૢ࡞ʢࣹӨม׵ɺ άϥϑ৞ΈࠐΈɺαϯϓϦϯάɺଛࣦؔ਺) • ඍ෼ՄೳͳϝογϡϨϯμϥʔ
70. PyTorch3D͸PyTorchͱ౷߹Ͱ͖ ΔΑ͏ʹͳ͍ͬͯΔɻ • ͢΂ͯͷPyTorch3DΦϖϨʔλ͸ҎԼΛຬͨ͢ɻ • PyTorchςϯιϧΛ࢖࣮ͬͯ૷͞Ε͍ͯΔɻ • ҟछσʔλͷϛχόονΛѻ͏͜ͱ͕Ͱ͖Δɻ • ඍ෼Մೳɻ • ΞΫηϥϨʔγϣϯʹGPUΛར༻Ͱ͖Δɻ
71. ҟछσʔλͷόονྫ
72. ެ։3DֶशϞσϧ Mesh R-CNN https://github.com/facebookresearch/meshrcnn
73. Ұؾʹ̏DσΟʔϓϥʔχϯ άͷݚڀ͕Ճ଎ͦ͠͏
74. Special Thanks
75. DeepL Translator (deepl.com) https://www.deepl.com/en/translator