tkow
December 19, 2016
310

# teratail_study

first step of understanding machine_learning

## tkow

December 19, 2016

## Transcript

7. ### ԿΛษڧ͢Ε͹ྑ͍ͷ͔  ϕΠζͷఆཧ  ઢܗճؼϞσϧ  ֬཰෼෍ ڞ໾ࣄલ෼෍ ࢦ਺෼෍ ΧςΰϦΧϧ෼෍

  χϡʔϥϧωοτ ͜ΕΒΛ͔ͬ͠Γԡ͑͞Δ͚ͩͰݟ௨͕͠ྑ͘ͳΓ·͢ɻ ػցֶशͰ࠷ॳʹԡ͓͑ͯ͘͞΂͖஌ࣝ

9. ###  ϕΠζͷఆཧ p(✓| x ) = p( x |✓)p(✓) R

p( x |✓)p(✓)d✓ ԾఆВ ͋ΔԾఆͷ ݩͰಘΒΕͨ σʔλY ಘΒΕͨσʔλ9͔ΒഎޙͷԾఆВΛ ਪఆ͢Δ جຊతͳ࿮૊Έ
10. ###  ϕΠζͷఆཧ جຊతͳ࿮૊Έ ಘΒΕͨσʔλू߹ͷ෼෍͔Β࠷దͳ෼෍Λਪఆ͢Δ ࠷ ໬ਪఆ  ࣄલ෼෍ΛԾఆͯ͠ಘΒΕͨσʔλू߹͔Βࣄલ෼෍ͷ࠷ దͳύϥϝʔλΛਪఆ͢Δ ."1ਪఆ

 ಘΒΕͨσʔλू߹͔ΒύϥϝʔλΛपลԽ ϕΠζਪఆ  p(✓| x ) = p( x |✓)p(✓) R p( x |✓)p(✓)d✓
11. ### ͳͥେࣄ͔ͲΜͳؔ਺Ͱ΋ύϥϝʔλΛ૿΍ͤ͹ۙࣅՄ ೳɻҰԠղੳղ͕ग़ͤΔࣄ͕ଟ͍ ݱ࣮࣌ؒͰղ͚Δͱ͸ ݴ͍ͬͯͳ͍ ɻ ඇઢܗͷϞσϧΛද͢ͷʹઢܗϞσϧ͕࢖ΘΕΔ χϡʔϥ ϧωοτͰ͸ɺγάϞΠυؔ਺ͳͲͷύϥϝʔλΛઢܗϞ σϧʹಥͬࠐΜͰ͍Δ ɻ

 ઢܗϞσϧ y = w0 + w1 1( x ) + · · · + wn n( x )
12. ### ϦϯΫؔ਺  ઢܗϞσϧ f (x) = w0 + w1 1(x)

+ . . . + wn n(x) f (x) ϦϯΫؔ਺ͱɺઢܗճؼϞσϧΛ૊Έ߹ΘͤΔͱɺϕΠζ ͷఆཧʹ౰ͯ͸Ίͯɺ࠷໬ਪఆ΍."1ਪఆ͕Ͱ͖Δɻ ྫ  ɹϦϯΫؔ਺ʹMPHJUؔ਺Λ౰ͯ͸Ίͯ࠷໬ਪఆΛղ͘ͱϩ δεςΟοΫճؼʹͳΔͳͲ

ͳΔ͔ͷ֬཰

15. ### ڞ໾ࣄલ෼෍ಛఆͷ໬౓ؔ਺ͷੵʹରͯ͠ɺࣄޙ෼෍ͷࣜ ͷܗ͕ಉ͡ࣄલ෼෍ͷ͜ͱɻ ڞ໾ࣄલ෼෍º໬౓͕ɺࣄޙ෼෍ͷܗͱಉ͡ʹͳΔ͜ͱΛ ར༻͢Δ͜ͱͰɺࣄޙฏۉͷެࣜΛద༻ͨ͠ΓɺϥϯμϜ αϯϓϦϯάͱݺ͹ΕΔख๏Λద༻͠΍͘͢Δ͜ͱ͕Ͱ͖ Δ σʔλ఺Λਫ૿ͯ͠͠શମͷ෼෍Λਪఆ͢Δํ๏ ɻ  ֬཰෼෍

p ( ✓ | x ) / p ( x | ✓ ) p ( ✓ ) ࣄલ෼෍ ࣄޙ෼෍ ໬౓ ϕʔλ෼෍㲌ϕϧψʔΠ෼෍ºϕʔλ෼෍ͳͲ
16. ### جຊతͳ࿮૊Έ ͋Δϊʔυʹ͓͚Δೖྗͷ࿨Λ׆ੑԽؔ਺ͱݺ͹ΕΔ೚ҙ ͷؔ਺ʹΑͬͯɺม׵͠ɺ࣍ͷೖྗ ग़ྗ ͱ͢Δ ͋ΔϊʔυʹมԽ͕ى͖ͨ࣌ʹશͯͷύϥϝʔλʹٴ΅͢ ӨڹΛࠩ෼ͷ࿈࠯཰Ͱද͢ɻ  χϡʔϥϧωοτ x1

x2 x3 f (x)=w1x1+w2x2+w3x3 y= ( f ( x )) y w1 w2 w3  
17. None
18. None
19. None
20. None