21.01.2015 Views

Chapter 2 Introduction to Neural network

Chapter 2 Introduction to Neural network

Chapter 2 Introduction to Neural network

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

¢£¤¥¦§ £ ¤¥¦¨<br />

¢¥¢¦§¡¢£¤¡¢ ¨©¢£¡£ ¡¢£ ¦£<br />

¡¢£¢¡¡¦£<br />

Example:<br />

Not linear separable!<br />

□<br />

Example: Classification problem<br />

©£ ¡<br />

□<br />

¢ ¥¢¦§<br />

¡¢£¤¡¢<br />

4.1 Perceptron training<br />

¢££¦¢<br />

Assume we have sampled the sensors when the process is OK (P)<br />

as well as when its broken (N). We have a number of input vec<strong>to</strong>rs<br />

in each class.<br />

Start: Choose w 0 randomly, t = 0<br />

test: Select a vec<strong>to</strong>r x ∈ P ∪ N<br />

If all x correct, s<strong>to</strong>p!<br />

36

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!