A Boolean Approach to Construct Neural Networks for Non-Boolean Problems
| Type of publication: | Conference paper |
| Citation: | Thimm-96.3 |
| Booktitle: | Proceedings of the 8th IEEE International Conference on Tools with Artificial Intelligence |
| Year: | 1996 |
| Month: | 11 |
| Organization: | IEEE |
| Abstract: | A neural network construction method for problems specified for data sets with in- and/or output values in the continuous or discrete domain is described and evaluated. This approach is based on a Boolean approximation of the data set and is generic for various neural network architectures. The construction method takes advantage of a construction method for Boolean problems without increasing the dimensions of the in- or output vectors, which is a strong advantage over approaches which work on a binarized version of the data set with an increased number of in- and output elements. Further, the networks are pruned in a second phase in order to obtain very small networks. |
| Userfields: | ipdhtml={https://www.idiap.ch/nn-papers/long_ICTAI/growing.html}, ipdmembership={learning}, |
| Keywords: | backpropagation neural networks, construction of networks, generalization, high order perceptrons, optimality criteria, pruning |
| Projects |
Idiap |
| Authors | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
Notes
|
|
|
|
|