ベイズで単回帰モデルを考える /bayes-simple-linear-regression
by
Thimblee
Link
Embed
Share
Beginning
This slide
Copy link URL
Copy link URL
Copy iframe embed code
Copy iframe embed code
Copy javascript embed code
Copy javascript embed code
Share
Tweet
Share
Tweet
Slide 1
Slide 1 text
ϕΠζͰ୯ճؼϞσϧΛߟ͑Δ 5IJNCMFF 1
Slide 2
Slide 2 text
ઃఆ ܇࿅σʔλͷઆ໌ม ͱతม ͔ΒҎԼͷ ༧ଌΛٻΊΔ ҎԼͷ୯ճؼϞσϧΛ༻͢Δ x = (x1 , x2 , ⋯, xN )T t = (t1 , t2 , ⋯, tN )T p(t* |x* , t, x) p(t* |x* , w, β) = 𝒩 (t* |w0 + w1 x* , β−1) 2
Slide 3
Slide 3 text
۩ମతʹ ͜͏͍͏σʔλʹର͍͍ͯ͠ײ͡ʹύϥϝʔλ Λௐͯ͠ɺઢ ΛҾ͖͍ͨɻ͜ͷσʔλେମ ͱͳ͍ͬͯΔɻ w = (w0 , w1 )T y = w0 + w1 x t = − 2 + 2x 3
Slide 4
Slide 4 text
ϕΠζͷఆཧ p(A|B) = p(A)p(B|A) p(B) 4
Slide 5
Slide 5 text
ࣄޙ QPTUFSJPS ύϥϝʔλɺ σʔλ ࣄޙΛ༻͍ͨύϥϝʔλͷਪఆ͕ϕΠζਪఆͰ͢ɻ w t p(w|t) = p(w)p(t|w) p(t) ∝ p(w)p(t|w) (posterior) ∝ (prior)(likelihood) 5
Slide 6
Slide 6 text
ࣄલ QSJPS p(w) = 𝒩 (w|0, α−1I), α = 0.25 6
Slide 7
Slide 7 text
ؔ MJLFMJIPPE L(w) = p(t|w) = 𝒩 (t|m, β−1I) where m = (w0 + w1 x1 , w0 + w1 x2 , ⋯, w0 + w1 xN )T, β = 2.0 7
Slide 8
Slide 8 text
ؔͷྫ ͜ͷΑ͏ͳ͍͍ײ͡ͷઢͩͱͱ͍͏େ͖͍ΛͱΔ L((−2.1,2.2)T) = 0.39 8
Slide 9
Slide 9 text
ؔͷྫ ͜ͷΑ͏ͳઢͩͱͱ͍͏ΛͱΔ L((−1.0,0.0)T) = 0.29 9
Slide 10
Slide 10 text
ؔͷྫ ͜ͷΑ͏ͳѱ͍ઢͩͱͱ͍͏খ͍͞ΛͱΔ L((1.0, − 3.0)T) = 0.18 10
Slide 11
Slide 11 text
ࣄલͱؔʢ࠶ܝʣ ؔ MJLFMJIPPE ࣄલ QSJPS 11
Slide 12
Slide 12 text
ࣄલͱؔͷੵ 12
Slide 13
Slide 13 text
ٻΊΒΕͨઢ ࣄޙ ͷ࣌ʹ࠷େʹͳΔ w = (−1.08,0.38) L((−1.08,0.38)T) = 0.31 13
Slide 14
Slide 14 text
͚ؔͩʢ࠷ਪఆʣͰ͍͍ͷͰ ϕΠζʢࣄޙʣͩͱσʔλΛ͏·͘දݱͰ͖͍ͯͳ͍ ࣮ࡍɺ͜ͷσʔλΛ୯ճؼϞσϧͰֶश͢ΔࡍʹϕΠζඞཁͳ͍ ʢ୯ճؼϞσϧ͕ཧղ͍͔͢͠Β༻͍ͨʣ ͔͠͠ɺҰൠʹϕΠζͰߟ͑ΔϝϦοτ͕ଟ͍ 14
Slide 15
Slide 15 text
ϕΠζͷಛ w ύϥϝʔλʢ୯ճؼϞσϧͳΒ ʣʹ͍ͭͯ֬Λߟ͑ΒΕΔ w ࣄલʹʢσʔλҎ֎ͷʣطͷใΛөͤ͞ΒΕΔ w ֬ͷஞ࣍ߋ৽͕Ͱ͖Δ w աֶशΛ͛Δʢਖ਼ଇԽʣ w ʢଞʹ৭ʑ͋Δͱࢥ͍·͢ʣ w 15
Slide 16
Slide 16 text
͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ 16