Abstract | ||
---|---|---|
An approach to neural network design based on processing and representing data at the event-space domain is presented. Analysis is then extended to processing structured objects. Decision functions based on nominal-valued structured objects can be evaluated at the event level, and parameters (e.g., weights) can be estimated analytically or adaptively. A type of this network on continuous-valued structured objects is presented based on partitioning of the outcome space such that each partitioned subspace corresponds to an input node in the network. The partitioning uses the maximum entropy criterion, applied iteratively on selected subspaces to produce a hierarchical partitioning of the outcome space. The criterion for the selection of subspaces can be based on class-entropy value such that subspaces with high degrees of class discrimination power are generated. The approach is illustrated in data analysis and image analysis problems |
Year | DOI | Venue |
---|---|---|
1993 | 10.1109/ICNN.1993.298686 | San Francisco, CA |
Keywords | Field | DocType |
image processing,iterative methods,neural nets,class discrimination power,class-entropy value,data analysis,event-space domain,event-space self-configurable neural network,image analysis,maximum entropy criterion,partitioned subspace,partitioning,structured objects,computer networks,process design,power generation,information science,maximum entropy,entropy,neural network,neural networks | Network on,Subspace topology,Pattern recognition,Iterative method,Computer science,Image processing,Linear subspace,Artificial intelligence,Principle of maximum entropy,Artificial neural network,Class discrimination | Conference |
Citations | PageRank | References |
0 | 0.34 | 3 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chiu, D.K.Y. | 1 | 29 | 3.30 |