Information retrieval and categorisation using a cell assembly network
Full text is not in this repository.
In this paper, CAs are applied to practical data mining tasks. The first is a standard categorisation task, the congressional voting task. The learning mechanisms allow this real world problem to be easily solved. An information retrieval task is also run. A straight forward neuron per word mechanism is used to represent documents. When a document is presented, all the neurons associated with each word are fired. The retrieval results are on par with existing IR methods. This shows the immediate applicability of the CA concept. CAs also provide a theoretical foundation for the long term development of cognitive architectures.
|Research Areas:||A. > School of Science and Technology > Computer Science
A. > School of Science and Technology > Computer Science > Artificial Intelligence group
|Depositing User:||Repository team|
|Date Deposited:||17 Oct 2008 12:16|
|Last Modified:||13 Oct 2016 14:11|
Actions (login required)