CANT 2.0

Sorry the code hasn't been transfered to the new server so the applets won't run

The CANT applet should appears when you look at one of the experiments. The applet version is incomplete, and doesn't allow you to write files. However, many experiments should be able to run. The code can be downloaded as a WinZip file; it should show more things and allow file writing. All of the experiments have not been written up yet (those without links), but should be runnable. If you have any problems feel free to contact c.huyck@mdx.ac.uk

Experiment 1 is from our 1999 Tech Report pg.10. A 30x30 net is generated with low connectivity, medium strength, and medium activation threshold, and it ignites and persists when presented with a stimulus.

Experiment 2 is from our 1999 Tech Report pg. 12. A 20x20 net is presented with varieties of a pattern for 20 cycles, then allowed to run for 30 more. As this is repeated, axonal strengths are increased, and eventually, the network persists for all of the additional 30 cycles.

Experiment 3 is from our 1999 Tech Report pg. 13 This is a 20x20 net, and is presented two types of patterns, neurons from the top half or neurons from the bottom half. It learns both of these CAs and one never ignites the other.

Experiment 4 is from our 2001 Tech Report pg. 5. This is a 20x20 net, and is presented two types of patterns, neurons from the top half or neurons from the bottom half, but the middle two rows appear in both. It shows that synapses quickly move to correlatory weights.

Experiment 5 is from our 2001 Tech Report pg. 15. This is a 20x20 net, and is presented two types of patterns, neurons from the top half or neurons from the bottom half, but the middle two rows appear in both. Using the compensatory learning rule, 2 overlapping CAs are formed.

Experiment persistence undone

Experiment has not been published. It generates a CA that persists for a considerable but not infinite time. undone

Experiment spontaneous activation undone

Experiment oscillation undone

Experiment 10 is from our Hierarchical CAs paper pg.7. It shows generated nets based on Hopfield weights that have properties of hierarchical categories.

Experiment 11 is from our Hierarchical CAs paper pg.12. Hierarchical CAs are formed.



Page last modified