Name
Abstract | ||
|---|---|---|
We propose a neural network model for the processing of fuzzy data. The network parameters (weights) are standard real numbers and the spreads at the output level result exclusively from uncertainty in the input data. Our network model performs `intelligent' inference calculations on the basis of fuzzy data and minimizes uncertainty in the final output.The number of free parameters (weights) in our network model coincides with the number of connections emanating from the various nodes. In this paper, though, we will refer only to the single node case. As usual, the learning mechanism corresponds to a non-linear regression over the network parameters.The local transfer functions associated with the nodes are more sophisticated than the standard ones. The difference is mainly in the preliminar integration module, in which the various local inputs contribute to the single total input to the node. Instead of the standard linear combination with the parameters \omega_i, our model weights each local input in a way which is inversely proportional to its spread (uncertainty). As a result, the more precise data are dominant in the local network computation. |
Year | DOI | Venue |
|---|---|---|
1995 | 10.1109/ANNES.1995.499483 | Dunedin |
Keywords | Field | DocType |
input data,network model,network parameter,precise data,model weight,neural network architecture,local transfer function,fuzzy data,neural network model,local network computation,local input,emulating fuzzy mappings,transfer functions,statistical analysis,robustness,neural network,free parameters,linear regression,transfer function,learning artificial intelligence,uncertainty,computer networks,nonlinear regression,intelligent networks,data processing,neural networks | Data mining,Linear combination,Computer science,Fuzzy logic,Algorithm,Robustness (computer science),Local area network,Intelligent Network,Artificial neural network,Network model,Free parameter | Conference |
ISBN | Citations | PageRank |
0-8186-7174-2 | 1 | 0.61 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mario Fedrizzi | 1 | 148 | 29.78 |
| Michele Fedrizzi | 2 | 342 | 20.01 |
| r a marques pereira | 3 | 90 | 8.76 |