Current Slide
Small screen detected. You are viewing the mobile version of SlideWiki. If you wish to edit slides you will need to use a larger device.
Building Neural Networks
-
Building a neural network for particular problems requires multiple steps:
- Determine the input and outputs of the problem;
- Start from the simplest imaginable network, e.g. a single feed-forward perceptron;
- Find the connection weights to produce the required output from the given training data input;
- Ensure that the training data passes successfully, and test the network with other training/testing data;
- Go back to Step 3 if performance is not good enough;
- Repeat from Step 2 if Step 5 still lacks performance; or
- Repeat from Step 1 if the network in Step 6 does still not perform well enough.
Speaker notes:
Content Tools
Tools
Sources (0)
Tags (0)
Comments (0)
History
Usage
Questions (0)
Playlists (0)
Quality
Sources
There are currently no sources for this slide.