275 reputation
1310
bio website
location
age
visits member for 2 years, 4 months
seen Dec 5 '12 at 15:20

May
6
accepted gradient descent rule
May
6
comment gradient descent rule
but perceptron is linear, isn't it?
May
6
comment gradient descent rule
well, for instance, in perceptron, you have w*x as your output. as you differentiate with respect to w_i you get set of Linear Equations. I guess maybe you meant full NN with hidden layers?
May
6
revised gradient descent rule
added 1 characters in body; edited title
May
6
comment gradient descent rule
my bad... spelling was not an issue, but funny comment indeed :)
May
6
asked gradient descent rule
May
5
accepted regression vs classification
May
5
asked regression vs classification
May
4
awarded  Supporter
May
4
awarded  Scholar
May
4
accepted Concavity proof help
May
4
comment Concavity proof help
got it ! thanks a lot :)
May
4
comment Concavity proof help
OK, what about the Right hand side? the right hand side has ax^2, not a^2x^2
May
4
revised Concavity proof help
added 93 characters in body
May
4
awarded  Editor
May
4
comment Concavity proof help
I modified my question to include my desired formula
May
4
comment Concavity proof help
I know, would you attempt solving it using the frmula in my comment?
May
4
comment Concavity proof help
Well, I meant if anyone could show it using the formula in my comment I would really appreciate it....
May
4
revised Concavity proof help
added 1 characters in body; edited title
May
4
comment Concavity proof help
Sorry, I meant concave... It does not seem to work. I know that f(ax + (1-a)y) >= af(x) + (1-a)f(y)