Professional Documents
Culture Documents
Gradient Descent Deep Learning: by T.K. Damodharan Vice President, RBS Reg - No: PC2013003013008
Gradient Descent Deep Learning: by T.K. Damodharan Vice President, RBS Reg - No: PC2013003013008
Gradient Descent Deep Learning: by T.K. Damodharan Vice President, RBS Reg - No: PC2013003013008
Deep Learning
By
T.K. Damodharan
Vice President, RBS
Reg.No: PC2013003013008
inputs outputs
x1 = 1 y1 = 1
x2 = 3 y2 = 2.2
w x3 = 2 y3 = 2
1 x4 = 1.5 y4 = 1.9
x5 = 4 y5 = 3.1
Goals:
Explore a number of linear training algorithms
ìï 1 if x =True üï
1[ x ] =í ý
î 0 if x =False
ï ï
þ
å 1[ y (w ×x + b) £0]
i i
i=1
You’re blindfolded, but you can see out of the bottom of the
blindfold to the ground right by your feet. I drop you off
somewhere and tell you that you’re in a convex shaped valley
and escape is at the bottom/minimum. How do you get out?
Finding the minimum
loss
w
One approach: gradient descent
Approach:
pick a starting point (w)
repeat: w
pick a dimension
move a small amount in that
dimension towards decreasing loss
(using the derivative)
One approach: gradient descent
Approach:
pick a starting point (w)
repeat:
pick a dimension
move a small amount in that
dimension towards decreasing loss
(using the derivative)
Gradient descent
n
d
=å exp(- yi (w ×xi + b)) - yi (w ×xi + b)
i=1 dw j
n
=å - yi xij exp(- yi (w ×xi + b))
i=1
Gradient descent
n
w j =w j + h å yi xij exp(- yi (w ×xi + b))
i=1
n
w j =w j + h å yi xij exp(- yi (w ×xi + b)) - hl w j
i=1
The update
w j =w j + h yi xij exp(- yi (w ×xi + b)) - hl w j