5.26 ( ) Consider a multilayer perceptron with arbitrary feed-forward topology, which is to be trained by
Question:
5.26 ( ) Consider a multilayer perceptron with arbitrary feed-forward topology, which is to be trained by minimizing the tangent propagation error function (5.127) in which the regularizing function is given by (5.128). Show that the regularization term Ω can be written as a sum over patterns of terms of the form
Ωn =
1 2
k
(Gyk)2 (5.201)
where G is a differential operator defined by G ≡
i
τi
∂
∂xi
. (5.202)
By acting on the forward propagation equations zj = h(aj), aj =
i wjizi (5.203)
with the operator G, show that Ωn can be evaluated by forward propagation using the following equations:
αj = h
(aj)βj, βj =
i wjiαi. (5.204)
where we have defined the new variables
αj ≡ Gzj, βj ≡ Gaj . (5.205)
Now show that the derivatives of Ωn with respect to a weight wrs in the network can be written in the form
∂Ωn
∂wrs
=
k
αk {φkrzs + δkrαs} (5.206)
where we have defined
δkr ≡ ∂yk
∂ar
, φkr ≡ Gδkr. (5.207)
Write down the backpropagation equations for δkr, and hence derive a set of backpropagation equations for the evaluation of the φkr.
Step by Step Answer:
Pattern Recognition And Machine Learning
ISBN: 9780387310732
1st Edition
Authors: Christopher M Bishop