Chapter 2 Introduction to Neural network
Chapter 2 Introduction to Neural network
Chapter 2 Introduction to Neural network
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
¡ ¢£ ¤¡¤¢¤£¥¦w x<br />
4.2 The Linear Neuron (LMS-algorithm)<br />
Is a neuron with a linear function<br />
Assume we have a signal x(n) which we want <strong>to</strong> transform linearly<br />
and match a signal d(n)<br />
¡<br />
x<br />
¢£ ¤¡¤¢¤£¥¦w x<br />
TDL L<br />
We form the error signal e(n) = d(n) − y(n). We define the instantaneous<br />
error function<br />
§<br />
J = 1 2 e(n)2<br />
We want <strong>to</strong> minimize J. we use the steepest descent approach and<br />
calculate ∇ w J<br />
∇ w J = ∇ w<br />
1<br />
2 (d(n) − wT x(n)) 2<br />
Used the chain rule and the equation become<br />
∇ w J = (d(n) − w T x(n)) · (−x(n)) = −e(n) · x(n)<br />
where the −x(n) is the inner derivative. The steepest descent states<br />
w k+1 = w k − α∇ w J<br />
w k+1 = w k + αe(n) · x(n)<br />
(LMS-algorithm)<br />
38