07 Perceptron

07 Perceptron - ECEN 649 Pattern Recognition Perceptrons...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
ECEN 649 Pattern Recognition Perceptrons Ulisses Braga-Neto ECE Department ECEN 649 Pattern Recognition – p.1/21
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Adjustable Discriminant Rules All the classification rules seen so far were plug-in rules, that is, they could be viewed as distribution estimation using training data. We will consider now a different idea: Assume a set of discriminants (decision boundaries) Search for the discriminant that best fits the data by optimizing some objective criterion ( “learning” ) This is the basic idea behind many popular “machine learning” classification rules: Perceptrons Support Vector Machines Neural Networks Decision Trees ECEN 649 Pattern Recognition – p.2/21
Background image of page 2
Rosenblatt’s Perceptron This was the first adjustable discriminant rule, proposed in the late 50’s by F. Rosenblatt . Assume a linear discriminant function g n ( x ) = a 0 + d s i =1 a i x i so that the designed classifier is given by ψ n ( x ) = b 1 , if a 0 + a i x i 0 0 , otherwise Adjust (“learn”) the parameters a 0 , a 1 , . . . , a d based on the training data. ECEN 649 Pattern Recognition – p.3/21
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Rosenblatt’s Perceptron - II This corresponds to the (single-layer) perceptron, depicted as follows. ECEN 649 Pattern Recognition – p.4/21
Background image of page 4
Given the feature vector x R d , consider the augmented vector: x = b 1 x B R d +1 so that the perceptron classifier is given by ψ n ( x ) = ± 1 , if a T x 0 0 , otherwise where a = [ a 0 , a 1 , . . . , a d ] T R d +1 is the parameter vector. ECEN 649 Pattern Recognition – p.5/21
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 6
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/08/2010 for the course ECEN 649 taught by Professor Staff during the Spring '08 term at Texas A&M.

Page1 / 21

07 Perceptron - ECEN 649 Pattern Recognition Perceptrons...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online