Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
AGI福岡 第3回
Search
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
yuky_az
November 14, 2024
Technology
0
110
AGI福岡 第3回
AGI時代に向けて、今からできることを共に考え、実行していこう!
yuky_az
November 14, 2024
Tweet
Share
More Decks by yuky_az
See All by yuky_az
AGI福岡 第8回
yukinaga
0
110
AGI福岡 第6回
yukinaga
0
120
AGI福岡 第5回
yukinaga
0
180
AGI福岡 第2回
yukinaga
0
120
生成AIの現状と展望: AIと共生する未来への道程
yukinaga
3
1.1k
BERTによる自然言語処理を学ぼう!【 Live!人工知能 #26】 #Live人工知能
yukinaga
0
420
iOSアプリは「感情」を宿すのか? AIとアプリの未来について
yukinaga
2
1.1k
iOSアプリに「意識」は宿るのか? ディープラーニングの先にある人工知能(AI)
yukinaga
6
6k
ヒトとAIの共生、そしてシンギュラリティ
yukinaga
0
1.1k
Other Decks in Technology
See All in Technology
Frontier Agents (Kiro autonomous agent / AWS Security Agent / AWS DevOps Agent) の紹介
msysh
3
180
ファインディの横断SREがTakumi byGMOと取り組む、セキュリティと開発スピードの両立
rvirus0817
1
1.6k
20260208_第66回 コンピュータビジョン勉強会
keiichiito1978
0
190
CDK対応したAWS DevOps Agentを試そう_20260201
masakiokuda
1
400
[CV勉強会@関東 World Model 読み会] Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models (Mousakhan+, NeurIPS 2025)
abemii
0
150
Amazon Bedrock Knowledge Basesチャンキング解説!
aoinoguchi
0
160
登壇駆動学習のすすめ — CfPのネタの見つけ方と書くときに意識していること
bicstone
3
130
22nd ACRi Webinar - NTT Kawahara-san's slide
nao_sumikawa
0
100
usermode linux without MMU - fosdem2026 kernel devroom
thehajime
0
240
We Built for Predictability; The Workloads Didn’t Care
stahnma
0
150
AWS Network Firewall Proxyを触ってみた
nagisa53
1
240
Agent Skils
dip_tech
PRO
0
130
Featured
See All Featured
BBQ
matthewcrist
89
10k
Optimizing for Happiness
mojombo
379
71k
Designing for Performance
lara
610
70k
The innovator’s Mindset - Leading Through an Era of Exponential Change - McGill University 2025
jdejongh
PRO
1
94
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
26
3.3k
A Guide to Academic Writing Using Generative AI - A Workshop
ks91
PRO
0
210
Heart Work Chapter 1 - Part 1
lfama
PRO
5
35k
Believing is Seeing
oripsolob
1
58
HDC tutorial
michielstock
1
390
Prompt Engineering for Job Search
mfonobong
0
160
Redefining SEO in the New Era of Traffic Generation
szymonslowik
1
220
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
54k
Transcript
"(*Ԭୈճ !ΤϯδχΞΧϑΣ
Φʔϓχϯά
ʮ൚༻ਓೳʢ"(*ʣʯͱʮಛԽܕਓೳʯ ൚༻ਓೳʢ˺ڧ͍"*ʣ ˠώτͷೳͷΑ͏ͳ൚༻ੑΛ࣋ͭ"* FHυϥ͑ΜɺమΞτϜͳͲ ಛԽܕਓೳʢ˺ऑ͍"*ʣ ˠݶఆతͳղܾਪ FHνΣεকعͷ"*ɺը૾ೝࣝͳͲ ࠷৽ͷ--.ͲͪΒʁ
"(*ͷొؒۙʁ 4*56"5*0/"-"8"3&/&44 ΑΓ IUUQTTJUVBUJPOBMBXBSFOFTTBJGSPNBHJ UPTVQFSJOUFMMJHFODF
ϊʔϕϧཧֶ © Johan Jarnestad/The Royal Swedish Academy of Sciences John
Hop fi eld and Geoffrey Hinton. Ill. Niklas Elmehed © Nobel Prize Outreach ͷϊʔϕϧཧֶɺ δϣϯɾ+ɾϗοϓϑΟʔϧυʢถࠃʣͱδΣϑϦʔɾ&ɾώϯτϯʢΧφμʣ͕ड
ϊʔϕϧཧֶ • डཧ༝ → ػցֶशͱਓχϡʔϥϧωοτϫʔΫͷج൫Λߏங͠ɺσʔλύλʔϯͷ هԱɾ࠶ݱΛՄೳʹͨ͠ޭɻ • ओͳۀ → ϗοϓϑΟʔϧυɿεϐϯܥͷཧֶͷݪཧΛԠ༻ͨ͠ʮϗοϓϑΟʔϧυ
ωοτϫʔΫʯΛ։ൃ͠ɺσʔλύλʔϯͷอଘͱ෮ݩΛ࣮ݱɻ → ώϯτϯɿʮϘϧπϚϯϚγϯʯΛ։ൃ͠ɺσʔλ͔ΒಛΛֶश͢Δٕज़ Λཱ֬ɻAIͱػցֶशͷඈ༂తͳਐలʹߩݙɻ • Өڹ → AIͱཧֶͷ༥߹ʹΑΔൃలΛଅਐ͠ɺԠ༻ͰͷՄೳੑΛେ͖֦͘େɻ
"(*Ԭͷҙٛ w "(*࣌ʹ͚ͯɺࠓ͔ΒͰ͖Δ͜ͱΛڞʹߟ͑ɺ ࣮ߦ͍ͯ͜͠͏ʂ
ӡӦऀհ w զ࠺ʢ4"*-BCגࣜձࣾʣ w ۙ౻ݑࣇʢגࣜձࣾελσΟετʣ w େ৴ߊʢ/0#%"5"גࣜձࣾʣ w ੨྄ʢςΠϧΠϯυגࣜձࣾʣ
දऀհ զ࠺ :VLJOBHB"[VNB !ZVLZ@B[ 4"*-BCגࣜձࣾදऔక w "*ؔ࿈ͷڭҭɺݚڀ w ཧֶത࢜ʢཧֶʣ w
๏େֶσβΠϯֶ෦݉ߨࢣ w 6EFNZͰສਓΛࢦಋ w ༗໊اۀͰ"*ݚमΛ୲ w ஶॻʹʮ͡ΊͯͷσΟʔϓϥʔχϯάʯͳͲ w झຯϒϥδϦΞϯॊज़"*Ξʔτ
ϋογϡλά BHJGVLVPLB
"(*Ԭ%JTDPSEίϛϡχςΟ
:PV5VCFϥΠϒ ʮ&OHJOFFSDBGF"(*ԬʯͰ:PV5VCFݕࡧ
ࠓճͷίʔυ IUUQTHJUIVCDPNZVLJOBHBIPQ fi FME@CPMU[NBOO
ϗοϓϑΟʔϧυωοτϫʔΫͱʁ
δϣϯɾϗοϓϑΟʔϧυࢯͷհ ݚڀऀͱͯ͠ͷܦྺ • ੜ·ΕɺΞϝϦΧͷཧֶऀɾੜཧֶऀ • ϓϦϯετϯେֶͰཧֶΛઐ߈ʢ1I%ʣ • ΧϦϑΥϧχΞՊେֶɺϓϦϯετϯେֶͳͲͰڭ佃 • ཧֶ͔ΒਆܦՊֶݚڀྖҬΛ֦େ
• ෳࡶܥͷݚڀͰଟେͳޭ ओͳۀͱධՁ • ɿϗοϓϑΟʔϧυωοτϫʔΫΛఏҊ • ཧֶͷ֓೦Λ༻͍ͯχϡʔϥϧωοτΛཧԽ • ݱͷਂֶशͷཧతج൫Λங͍ͨઌۦऀͷҰਓ Ill. Niklas Elmehed © Nobel Prize Outreach
ϗοϓϑΟʔϧυωοτϫʔΫͷݩจ ถࠃՊֶΞΧσϛʔلཁʹܝࡌ IUUQTXXXQOBTPSHEPJQOBT
جຊΞʔΩςΫνϟ ωοτϫʔΫߏ • ͯ͢ͷχϡʔϩϯ͕૬ޓʹ݁߹ • ֤χϡʔϩϯํʹଓɺͨͩࣗ͠ݾ݁߹ଘࡏ͠ͳ͍ • ݁߹ͷॏΈରশతʢ ʣ •
χϡʔϩϯͷঢ়ଶࢄʢ ʣ·ͨೋʢ ʣ ಈ࡞ͷಛ • ΤωϧΪʔؔ ʹجͮ͘ঢ়ଶߋ৽ ◦ ɿχϡʔϩϯ ͷᮢʢόΠΞεʣ • ඇಉظతͳঢ়ଶߋ৽ʢҰʹͭͷχϡʔϩϯʣ • ہॴతͳใͷΈͰߋ৽அ • ΤωϧΪʔ࠷খԽʹΑΔ҆ఆঢ়ଶͷऩଋ • ཧֶͷεϐϯάϥεϞσϧͱྨࣅͨ͠ৼΔ͍ wij = wji si ∈ − 1, + 1 si ∈ 0,1 E = − 1 2 ∑ i,j wij si sj − ∑ i θi si θi i
ಈ࡞ݪཧ ঢ়ଶߋ৽ͷϝΧχζϜ • ֤χϡʔϩϯͷೖྗɿ • ߋ৽نଇɿ ࢄʢۃੑʣͷ߹ɿ ೋʢ୯ۃੑʣͷ߹ɿ
• ඇಉظతͳߋ৽ʢϥϯμϜʹબΜͩͭͷχϡʔϩϯΛߋ৽ʣ • ͯ͢ͷχϡʔϩϯ͕҆ఆ͢Δ·Ͱ܁Γฦ͠ hi = ∑ j wij sj + θi si = { +1 JG hi ≥ 0 −1 JG hi < 0 si = { 1 JG hi ≥ 0 0 JG hi < 0
ಈ࡞ݪཧ ΤωϧΪʔͱऩଋ • ΤωϧΪʔؔঢ়ଶߋ৽ʹΑΓ୯ௐݮগ • γεςϜඞͣہॴ࠷খʹऩଋ • ࠷ऴঢ়ଶॳظঢ়ଶʹґଘ • ΤωϧΪʔܗͷΠϝʔδɿ
◦ࢁʢෆ҆ఆঢ়ଶʣ͔Β୩ʢ҆ఆঢ়ଶʣ ◦ෳͷ҆ఆঢ়ଶʢہॴ࠷খʣ͕ଘࡏ ◦هԱύλʔϯ҆ఆঢ়ଶͷҰͭʹରԠ
ֶशͱهԱ ֶशʢॏΈͷܾఆʣ • ݁߹ՙॏͷֶशଇɿ ʢ ʣ ◦ ɿχϡʔϩϯ ◦ ɿهԱͤ͞Δύλʔϯ
◦ ɿύλʔϯ ʹ͓͚Δχϡʔϩϯ ͷঢ়ଶ • ҰͷܭࢉͰॏΈΛܾఆʢඇ෮తʣ • ੜֶతͳϔϒଇʹجͮ͘ هԱ༰ྔͱಛ • ཧతͳهԱ༰ྔɿ ◦ ݸͷχϡʔϩϯͰ ݸͷύλʔϯΛهԱՄೳ • ϊΠζΛؚΉೖྗ͔Βͷى͕Մೳ • ύλʔϯͷҰ෦͔ΒશମΛ࠶ߏ wij = 1 N ∑p μ=1 sμ i sμ j i ≠ j N p sμ i μ i pmax ≈ 0.14N N 0.14N
Ԡ༻ྫͱಛ දతͳԠ༻ྫ • ࿈هԱγεςϜ ◦ύλʔϯ෮ݩɾϊΠζআڈ ◦ෆશͳೖྗ͔Βͷى • Έ߹Θͤ࠷దԽ ◦८ճηʔϧεϚϯ ◦εέδϡʔϦϯά
རͱݶք • རɿฒྻॲཧ͕ՄೳɺϋʔυΣΞ࣮͕༰қ • ݶքɿهԱ༰ྔͷ੍ݶʢ ʣɺہॴղʹؕΔՄೳੑ 0.14N
ൃలͱӨڹ తͳൃల • ϘϧπϚϯϚγϯͷਐԽ ◦֬తͳৼΔ͍ͷಋೖɺӅΕͷՃ • ࿈ଓϞσϧͷ։ൃ ◦ΞφϩάχϡʔϩϯͷಋೖɺΑΓ๛͔ͳදݱೳྗͷ֫ಘ ݱͷӨڹ •
ཧֶͷݟͷ׆༻ ◦ΤωϧΪʔ࠷খԽʹΑΔֶश ◦֬తΞϓϩʔνͷجૅ
ϗοϓϑΟʔϧυωοτϫʔΫͷίʔυ IUUQTHJUIVCDPNZVLJOBHBIPQ fi FME@CPMU[NBOOUSFFNBJOTFDUJPO@
ϘϧπϚϯϚγϯͱʁ
δΣϑϦʔɾώϯτϯࢯͷհ Ill. Niklas Elmehed © Nobel Prize Outreach ܦྺͱݚڀ •
ΠΪϦεੜ·ΕɺʮσΟʔϓϥʔχϯάͷʯ • τϩϯτେֶڭतɺ(PPHMF3FTFBSDIॴଐ • ೝ৺ཧֶ͔Βਓೳݚڀ • ਂֶशͷཧతجૅΛཱ֬ ओͳۀ • ޡࠩٯ๏ͷ࠶ൃݟʢʣ • %FFQ#FMJFG/FUXPSLͷఏҊʢʣ • νϡʔϦϯάडʢʣ • "*҆શੑͷܯʢʣ
ϘϧπϚϯϚγϯͷݩจ τϩϯτେֶͷΣϒαΠτʹܝࡌ IUUQTXXXDTUPSPOUPFEVdGSJU[BCTQTDPHTDJCNQEG
എܠͱੜ ։ൃͷഎܠ • ɺϗοϓϑΟʔϧυωοτϫʔΫͷݶք • ౷ܭྗֶʢϘϧπϚϯʣͷԠ༻Λண • )JOUPO4FKOPXTLJʹΑΔڞಉݚڀʢʣ • ֬తͳৼΔ͍ͷಋೖ
ओཁͳֵ৽ • ֬తͳχϡʔϩϯͷಋೖ • ԹύϥϝʔλʹΑΔ੍ޚ • ӅΕϢχοτͷಋೖ • ΤωϧΪʔ࠷খԽͱ֬తֶशͷ౷߹
جຊΞʔΩςΫνϟ ωοτϫʔΫߏ • ՄࢹͱӅΕͷߏ • ͯ͢ͷϢχοτ͕ؒํʹ݁߹ • ֬తͳঢ়ଶભҠɿ ◦
ɿঢ়ଶมԽʹ͏ΤωϧΪʔมԽ ◦ ɿԹύϥϝʔλ ΤωϧΪʔؔ • ◦ ɿϢχοτؒͷ݁߹ॏΈ ◦ ɿϢχοτͷঢ়ଶʢ·ͨʣ ◦ ɿόΠΞε߲ • Թ ʹΑͬͯঢ়ଶΛ੍ޚ p(si = 1) = 1 1 + e−ΔEi/T ΔEi T E = − ∑ i<j wij si sj − ∑ i θi si wij si θi T
ಈ࡞ϝΧχζϜ ঢ়ଶભҠͷΈ • ϘϧπϚϯʹै͏֬తͳঢ়ଶߋ৽ ◦ ◦ ɿؔ ɿશϢχοτͷঢ়ଶϕΫτϧ •
ΪϒεαϯϓϦϯάʹΑΔঢ়ଶભҠ ◦ϥϯμϜʹબΜͩϢχοτΛ֬తʹߋ৽ ◦ฏߧঢ়ଶʹ౸ୡ͢Δ·Ͱ܁Γฦ͠ Թ੍ޚͱ࠷దԽ • γϛϡϨʔςουΞχʔϦϯάͷར༻ ◦ߴԹ͔Β։࢝͠ɺঃʑʹԹΛԼ͛Δ ◦ہॴղճආͱେҬత࠷దԽ • ԹʹΑΔ୳ࡧɾऩଋͷ੍ޚ ◦ߴԹɿϥϯμϜͳ୳ࡧԹɿہॴతͳ࠷దԽ P(s) = 1 Z e−E(s)/T Z s
ֶशΞϧΰϦζϜ ֶशͷجຊࣜ • ॏΈߋ৽ଇɿ ◦ ɿֶश ◦ ɿσʔλͷظʢਖ਼૬ʣ ◦
ɿϞσϧͷظʢෛ૬ʣ ্࣮ͷ • ίϯτϥεςΟϒμΠόʔδΣϯεʢ$%ʣ๏ͷಋೖ ◦શͳऩଋΛͨͣʹֶश ◦গεςοϓͷαϯϓϦϯάͰ༻ • Թεέδϡʔϧͷઃఆ ◦ֶशॳظߴԹͰ୳ࡧతʹ ◦ֶशޙظԹͰऩଋΛଅਐ Δwij = η(⟨si sj ⟩data − ⟨si sj ⟩model ) η ⟨ ⋅ ⟩data ⟨ ⋅ ⟩model
ൃలͱԠ༻ Ϟσϧͷൃల • ੍ݶϘϧπϚϯϚγϯʢ3#.ʣͷߟҊ ◦ؒͷΈͷ݁߹ʹΑΔޮԽ ◦%FFQ#FMJFG/FUXPSLͷجૅʹ • %FFQ-FBSOJOHֵ໋ͷߩݙ ◦ਂֶशͷࣄલֶशख๏ͱͯ͠׆༻ ◦ੜϞσϧͷجຊ֓೦Λཱ֬
ϘϧπϚϯϚγϯͷίʔυ IUUQTHJUIVCDPNZVLJOBHBIPQ fi FME@CPMU[NBOOUSFFNBJOTFDUJPO@
Ԭͷ"(* Γ্͍͖͛ͯ·͠ΐ͏ʂ