ln022 - Neural Network Learning Here we look at the...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
Neural Network Learning Here we look at the practical considerations for constructing artificial neural networks: (1) All training data has to be numerical , even categorical data has to be mapped into numerical values (sub-symbolic learner) (2) It is customary to normalize the data into the interval [0,1], or something close to it. (3) We need to pick a topology for the network Do we need a hidden layer? If so, how many nodes in the hidden layer? (4) We need to pick a learning rate . (5) We need to pick a convergence criterion that will tell us whether we learned the concept/training examples successfully.
Background image of page 1

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

View Full DocumentRight Arrow Icon
Tiberius Data Mining Suite Create a new neural network.
Background image of page 2
Tiberius Data Mining Suite Select a CSV file for training. NOTE: ignore the tip dialog box.
Background image of page 3

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

View Full DocumentRight Arrow Icon
Select the neural network inputs and output; the inputs are given by your independent attributes, the output is your target attribute. Hit OK when
Background image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 10/03/2011 for the course CSC 592 taught by Professor Staff during the Spring '11 term at Rhode Island.

Page1 / 10

ln022 - Neural Network Learning Here we look at the...

This preview shows document pages 1 - 5. Sign up to view the full document.

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