Hybrid NN-DT cascade method for generating decision trees from backpropagation neural networks
Transforming knowledge between connectionist and symbolic machine learning approaches is not a uniform task and there is no general recipe for performingit. Irrespective of the way the transformation of knowledge, the developed methods usually fall into two classesČ methods with high rate of transfo...
Shranjeno v:
| Main Authors: | , |
|---|---|
| Format: | Book Chapter |
| Jezik: | English |
| Teme: | |
| Sorodne knjige/članki: | Vsebovano v:
Proceedings of the 9th international conference on neural information processing (ICONIP'02) |
| Oznake: |
Označite
Brez oznak, prvi označite!
|
| LEADER | 01901naa a2200205 ib4500 | ||
|---|---|---|---|
| 001 | 7578390 | ||
| 003 | SI-MaCOB | ||
| 005 | 20121003000000.0 | ||
| 008 | 021217s2002 si |||||s|||||||| ||eng c | ||
| 040 | |a KTFMB |b slv |c SI-MaIIZ |e ppiak | ||
| 041 | 0 | |a eng |b eng | |
| 080 | |a 004.8 | ||
| 100 | 1 | |a Zorman, Milan. |4 aut | |
| 245 | 0 | 0 | |a Hybrid NN-DT cascade method for generating decision trees from backpropagation neural networks |h [Elektronski vir] / |c Milan Zorman, Peter Kokol. |
| 300 | |a [5] str. | ||
| 520 | |a Transforming knowledge between connectionist and symbolic machine learning approaches is not a uniform task and there is no general recipe for performingit. Irrespective of the way the transformation of knowledge, the developed methods usually fall into two classesČ methods with high rate of transformed knowledge is done, but with a lot of restrictions concerning the type of data in the training sets, training methods, and the size of data setsč and methods with moderate rate of transformed knowledge, but with less restrictions. Our main interest was to find or develop a technique that would possess the knowledge acquisition power of neural networks and explanation power of decision trees. That is why we developed a NN-DT Cascade method, an embedded hybrid of neural networks and decision trees, which is capable of transforming a part of knowledge from the neural network into a decision tree. | ||
| 653 | 0 | |a odločitvena drevesa |a transformacija znanja |a strojno učenje |a nevronske mreže |a kaskadne metode | |
| 653 | 0 | |a decision trees |a knowledge transformation |a machine learning |a neural networks |a cascade methods | |
| 700 | 1 | 2 | |a Kokol, Peter, |d 1957- |4 aut |
| 773 | 0 | |a International conference on neural information processing (9 : 2002 : Singapore) |t Proceedings of the 9th international conference on neural information processing (ICONIP'02) |d [Singapore : IEEE, 2002] |w 7577878 |z 981047525X |g [5] str. | |