assignment-3

assignment-3 - CSC592CM Programming Assignment #3 Due...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon

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

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

Unformatted text preview: CSC592CM Programming Assignment #3 Due 12/20/06 at 3pm in the CS Office Version 1.0 1 Neural Networks Neural networks can learn classifications from data. To train a neural network we need to provide it with examples of the classification task. The following is a simple dataset that assigns each point described by ( X 1 ,X 2) a label Y {- 1 , 1 } , X 1 X 2 Y 1 6- 1 1 4 1 2 1 1 2 . 5 1 . 5 1 3 7- 1 3 1 1 4 1- 1 5 3- 1 The goal is to have the neural network learn a classification from this data so that for example given the point (1 , 6) it will return a- 1. In addition, once we have learned a classification we can predict what the outcome or labels of points not in the dataset might be. For example, we could predict the label for the point (5 , 5)? Perhaps the simplest neural network is the Rosenblatt Perceptron : 1 This neural network consists of a single neuron that performs a weighted sum of the network inputs (including a bias term b ) and then performs a thresholding step. Notice) and then performs a thresholding step....
View Full Document

Page1 / 2

assignment-3 - CSC592CM Programming Assignment #3 Due...

This preview shows document pages 1 - 2. Sign up to view the full document.

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