The Use of Output Combiners in Enhancing the Performance of Large Data for ANNs
Deriving classification information from large databases presents several challenges. The current methods used to classify a large dataset have the disadvantage of requiring long computational time and high complexity. In addition, most of the methods can only deal with selected features of the data...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
2014
|
| Subjects: | |
| Online Access: | http://eprints.unisza.edu.my/4838/1/FH02-FIK-14-00846.jpg http://eprints.unisza.edu.my/4838/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Deriving classification information from large databases presents several challenges. The current methods used to classify a large dataset have the disadvantage of requiring long computational time and high complexity. In addition, most of the methods can only deal with selected features of the data while some of the methods can only deal with categorical or numerical attributes. This paper proposes large data solutions by defining the strategy to classify large data with local processors of Artificial Neural Networks (ANNs). A combination technique for reordered ANNs is proposed in modeling the combination of multiple ANNs as part of framework approach. Several repeated experiments with different techniques tested with the MNIST dataset show good percentage of performance and reduction of errors. The results obtained are in line with the importance of good performance achieved with the use of combiner for a large data solution. |
|---|