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

クックパッドと機械学習（短縮版）/MLTBP

j.harashima
March 28, 2019
0
8k

 クックパッドと機械学習（短縮版）/MLTBP

j.harashima

March 28, 2019
Tweet

More Decks by j.harashima

See All by j.harashima
日本語レシピデータセットの継続的な構築と複合的な利用/JED2022
junharashima
0
10k
自然言語処理の基礎と応用 〜 料理と医療を題材として 〜 /JADI2021
junharashima
0
4.2k
企業での研究開発の楽しさと苦労/WAP-Tech-Talk
junharashima
1
9.8k
クックパッドにおける研究開発/HCG2020
junharashima
0
3.5k
Calorie Estimation in a Real-World Recipe Service/iaai-20
junharashima
0
13k
クックパッドと NLP/CV/nlpaper-challenge
junharashima
0
80
AI 部門の実戦投入/repro-tech-meetup
junharashima
0
3.5k
クックパッドと機械学習/uec-aix-seminar
junharashima
0
10k
実データにふれる自然言語処理インターンシップ/internship2018
junharashima
1
14k

Featured

See All Featured
Measuring & Analyzing Core Web Vitals
bluesmoon
4
170
Scaling GitHub
holman
458
140k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
26
1.9k
Building an army of robots
kneath
302
44k
Side Projects
sachag
452
42k
Speed Design
sergeychernyshev
25
670
The Pragmatic Product Professional
lauravandoore
32
6.3k
Building a Scalable Design System with Sketch
lauravandoore
460
33k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
26
1.5k
Rebuilding a faster, lazier Slack
samanthasiow
79
8.7k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
28
9.1k
Fontdeck: Realign not Redesign
paulrobertlloyd
82
5.3k

Transcript

  1. .BDIJOF-FBSOJOH5FBN#VJMEJOH1JUDI ΫοΫύουͱػցֶशɹ ΫοΫύουגࣜձࣾݪౡ७ ʢ୹ॖ൛ʣ

  2. ೥݄ ೥݄ ژ౎େֶࠇڮɾՏݪݚڀࣨ഑ଐ ΫοΫύουೖࣾɺαʔϏε։ൃ෦໳഑ଐ ത࢜ʢ৘ใֶʣऔಘ ΤϯδχΞʢ3VCZPO3BJMTػցֶशʣ ೥݄ Ϧαʔνϟʔʢࣗવݴޠॲཧ৘ใݕࡧʣ ݪౡ७ ೥݄

    Ϛωʔδϟʔʢਓࣄ޿ใࡒ຿ʜʣ ݚڀ։ൃ෦໳৽ઃɺಉ෦໳഑ଐ

  3. ΫοΫύου Πϯλʔωοτ্ͰϨγϐͷ౤ߘɾݕࡧ౳͕Ͱ͖Δ ೔ຊ࠷େͷྉཧϨγϐαʔϏε

  4. Ԋֵ ೥݄ ༗ݶձࣾίΠϯʢݱΫοΫύουגࣜձࣾʣઃཱ ೥݄ ೥݄ ೥݄ ೥݄ ೥݄ ೥݄ Ϩγϐͷ౤ߘɾݕࡧαʔϏεLJUDIFO!DPJO։࢝

    ΫοΫύουʹαʔϏε໊มߋ ೥݄ ϓϨϛΞϜαʔϏε։࢝ Ϛβʔζ্৔ ౦ূҰ෦ʹࢢ৔มߋ ೥݄ ւ֎ల։Λຊ֨Խ ઃཱप೥ ϓϨϛΞϜαʔϏεձһ਺ສਓಥഁ

  5.  ݴޠΧࠃ

  6.  ݴޠΧࠃ

  7. ϓϨϛΞϜձһ਺ ݄ؒར༻ऀ਺ʢࠃ಺ʣ ݄ؒར༻ऀ਺ʢւ֎ʣ Ϩγϐ਺ ສਓ ສ඼ ສ඼  ສਓ 

    ສਓ

  8. Ԋֵ ೥݄ ༗ݶձࣾίΠϯʢݱΫοΫύουגࣜձࣾʣઃཱ ೥݄ ೥݄ ೥݄ ೥݄ ೥݄ ೥݄ Ϩγϐͷ౤ߘɾݕࡧαʔϏεLJUDIFO!DPJO։࢝

    ΫοΫύουʹαʔϏε໊มߋ ೥݄ ϓϨϛΞϜαʔϏε։࢝ Ϛβʔζ্৔ ౦ূҰ෦ʹࢢ৔มߋ ϓϨϛΞϜαʔϏεձһ਺ສਓಥഁ ೥݄ ւ֎ల։Λຊ֨Խ ઃཱप೥ ೥݄ ݚڀ։ൃ෦໳৽ઃ

  9. എܠ ʕʕ·ͣ͸ɺݚڀ։ൃ෦͕ੜ·Εͨഎܠʹ͍ͭͯڭ͍͑ͯͩ͘͞ɻ ɹݚڀ։ൃ෦্ཱ͕͕͖͔͚ͪͬͨͬ͸ɺ೥͝Ζʹࣾ಺ͰػցֶशͳͲʹڵຯΛ࣋ͬͨࣾһ͕਺໊ू·ͬͯݚڀ ։ൃνʔϜΛ࡞Γɺۀ຿֎Ͱࣗओతʹٕज़ͷݚڀΛ͸͡Ίͨͱ͜Ζʹ͔͞ͷ΅Γ·͢ɻΫοΫύου͸αʔϏεͷӡӦ Λ௨ͯ͡ɺ͞·͟·ͳϢχʔΫͳσʔλΛอ༗͍ͯͨ͠ͷͰɺͦΕΒͱػցֶशΛ૊Έ߹ΘͤΔ͜ͱͰ໘ന͍αʔϏε ͕࡞Εͳ͍͔ͱߟ͍͑ͯͨͷͰ͢ɻ ɹ౰࣌ɺͦΕ͸ձࣾʹͱͬͯ͸͋͘·Ͱlඇެࣜzͳ׆ಈͩͬͨͷͰ͕͢ɺͨͱ͑͹ΫοΫύουͷϏοάσʔλΛݚڀ ໨తͱͯ͠େֶͷݚڀࣨʹఏڙ͢Δͱ͍ͬͨ׆ಈΛଓ͚ΔதͰɺࣾ಺Ͱ΋஫໨͞ΕΔΑ͏ʹͳΓ·ͨ͠ɻ͢Δͱɺ ೥͝Ζ͔Β͸ੈͷதͰػցֶशʹେ͖ͳ஫໨͕ू·ΔΑ͏ʹͳΓɺͦΕʹͱ΋ͳͬͯࣾ಺ͷ͞·͟·ͳ෦ॺ͔ ΒɺࢲͨͪʹػցֶशΛ׆༻ͨ͠αʔϏε΁ͷ։ൃࢧԉͷ੠ֻ͕͔ΔΑ͏ʹͳͬͨͷͰ͢ɻ

    ɹͦ͏ͳΔͱɺػցֶश͕ಘҙͳΤϯδχΞ͕ධՁ͞ΕΔ૊৫͕ࣾ಺ʹͳ͍ͱ͍͏՝୊͕ੜ·Εͯ͠·͍·͢ɻ౰࣌ɺ ͦ͏͍͏ΤϯδχΞ͸͞·͟·ͳ෦ॺʹϔϧϓʹ͍ͬͯ׆ಈ͍ͯͨ͠ͷͰɻͦ͏ͨ͠૊৫తͳ՝୊ͱɺੈͷதͷػց ֶशʹؔ͢ΔϜʔϒϝϯτͳͲΛഎܠʹɺ೥݄ʹݚڀ։ൃࣨͱͯ͠ਖ਼ࣜͳࣾ಺νʔϜ͕Ͱ͖ɺ݄ʹ෦ʹঢ֨ ͠·ͨ͠ɻ

  10. ؔ࿈αʔϏε ͓·͔ͤ੔ཧ ०ͷ໺ࡊϨγϐ΍ ϝΠϯʹ࢖͑ΔϨγϐ͕ ͙͢ʹݟ͔ͭΔ "MFYBεΩϧ ࢖͍͍ͨࡐྉ͚ͩͰ ͙͢ʹ࡞ΕΔਓؾͷϨγϐఏҊ ྉཧ͖Ζ͘ ࡱΔ͚ͩͰه࿥ʹʂ

    ͋ͳͨͷ͓ྉཧࣸਅΛ ࣗಈͰ੔ཧ Ϩγϐͷͦͷઌ΁ ͓͍͍͠εϚʔτΩονϯ 0J$Z

  11. ਓ਺ ʢׅހ಺͸.-ܥͷਓ਺ʣ        

         ਓ ਓ ਓ ਓ ਓ ਓ ϋʔυ΢ΣΞܥͷνʔϜ͕ ผ෦໳ͱͯ͠εϐϯΞ΢τ

  12. .-ܥͷτϐοΫʢҰྫʣ ࣗવݴޠॲཧ ɾ&ODPEFS%FDPEFSʹΑΔࡐྉ໊ͷਖ਼نԽ ɾ-45.ʹΑΔඇखॱͷݕग़ ɾGBTU5FYUʹΑΔࡐྉͷϨίϝϯυ ը૾ೝࣝ ɾ*ODFQUJPOWʹΑΔྉཧࣸਅͷநग़΍෼ྨ ɾ.PCJMF/FUʹΑΔݟӫ͑͢Δྉཧࣸਅͷநग़ ɾ43("/ʹΑΔྉཧࣸਅͷ௒ղ૾ .-0QT

    ɾ4MBDL$IBU#PUʹΑΔ&$Πϯελϯεͷ؅ཧ ɾ%PDLFSͱDPPLJFDVUUFSʹΑΔϓϩδΣΫτͷ؅ཧ ɾ&$4ʹΑΔΞϓϦͷσϓϩΠ΍%8)ʹΑΔσʔλͷ؅ཧ ΦʔϓϯαΠΤϯε ɾݚڀ༻Ϩγϐσʔλͷެ։ʢXࠃཱ৘ใֶݚڀॴʣ ɾ֤छίϯϖςΟγϣϯͷ࣮ࢪʢX಺ֳ෎ɺਓ޻஌ೳֶձɺʜʣ ɾ࿦จͷࣥචʢ೥Ͱຊ͕࠾࿥ʣ .-ܥ͸ਓ

  13. ৄ͘͠͸ BOENPSF

  14. ͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ