We aren't endorsed by this school
CS 156 - Caltech Study Resources
• 20 Pages
ITunesU_Lecture01_April_03

School: Caltech

• 25 Pages
ITunesU_Lecture09_May_01

School: Caltech

E N = E + D E f H E N H f E E g (D)(x) g (x) f (x) E N N

• 25 Pages
ITunesU_Lecture03_April_10

School: Caltech

g h 1 , h2 , , hM Hi |E (g ) E (g )| > Eout(h) |E (h1) E (h1)| > |E (h2) E (h2)| > |E (hM ) E (hM )| > Ein(h) Hi P[ 22N |E (h) E (h)| > ] 2e M

• 22 Pages
ITunesU_Lecture10_May_03

School: Caltech

x0 x1 s h(x) x2 xd E (s) w w(0) (ynwxn) P (yn | xn) = n=1 w(t + 1) = w(t) E (w(t) N N n=1 t = 0, 1, 2, w N 1 E (w) = N h(xn), yn n=1 ln(1+eynw xn )

• 23 Pages
ITunesU_Lecture04_April_12

School: Caltech

d wixi = w x i=0 h(x) = (wx) h(x) = wx 1 w = (X X) X y y x1 x2 wx w x z (x1, x2) (x2, x2) 12

• 25 Pages
ITunesU_Lecture07_April_24

School: Caltech

mH(N ) H N 1 2 3 4 5 6 : 1 1 1 1 1 1 1 : Hoeffding Inequality Union Bound VC Bound k k 23456 22222 34444 4 7 top 8 8 8 5 11 . . . . . . 6: . 7: . : . bottom k1 mH(N ) i=0 . . . . . . . . . . N i N k1 space of data sets . D (a) [ |E (b) (c) [ |E

• 23 Pages
ITunesU_Lecture08_April_26

School: Caltech

d(H) 10 10 5 10 H 0 10 5 10 up 20 UNKNOWN TARGET FUNCTION f: X Y 80 100 120 140 160 180 200 N d DISTRIBUTION on X TRAINING EXAMPLES ( x1 , y1 ), . , ( xN , y ) N ALGORITHM 60 PROBABILITY P LEARNING 40 FINAL HYPOTHESIS g~f ~ A E HYPOTH

• 18 Pages
ITunesU_Lecture02_April_05

School: Caltech

_ + + _ + + _ y = f (x) (x1, y1), , (xN , yN ) H + _ gf

• 21 Pages
ITunesU_Lecture05_April_17

School: Caltech

y = f (x) h(x), f (x) 8 >+1 < > : 1 1 E (h) = N target function f: x) XY plus noise TRAINING EXAMPLES ( x1 , y1 ), . , ( xN , y ) N UNKNOWN INPUT DISTRIBUTION P (x) N h(xn), f (xn) n=1 (x1, y1), , (xN , yN ) E (h) = Ex P (x, y ) = P (x)P (y

• 19 Pages
ITunesU_Lecture06_April_19

School: Caltech

mH(N )= max x1, ,xN X |H(x1, , xN )| x1 x2 x3 mH(N ) mH(N ) M mH(N ) mH(N ) mH(N ) B (N, k ) N

• 24 Pages
ITunesU_Lecture11_May_08

School: Caltech

1 + + + + + + + + + + x2 1 x1 1 x 1 l L (l) xj = d s l = L (s) xd + + h (x ) (l1) (l) j (l ) wij = xi (l1) (l) wij i=0 (s) = tanh(s) (l1) xi d( l ) (l1) i (l) (l1) 2 = (1 (xi ) (l) wij j j =1

Back to course listings