TIIE EFFECT OF RATIO BETWEEN TRAINING AI'iD TESTING SETS IN MODEL SELECTION FOR NEURAL NETWORKS CLASSIFICATION
Dctennining the large ofsample sia is hig}ly contexr dependent- In genemt, the larger the din)ension of paramel€r, the larger sample size must be to obtain a given deeree of approximatio.. In nan! cases ofNN application, the data set is randomly split inio two mnrually exclu...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
2006
|
| Subjects: | |
| Online Access: | https://repository.ugm.ac.id/32917/1/2.pdf |
| _version_ | 1797020195216162816 |
|---|---|
| author | rezeki, sri Subanar, Subanar Suryo, Guritno |
| author_facet | rezeki, sri Subanar, Subanar Suryo, Guritno |
| author_sort | rezeki, sri |
| collection | UGM |
| description | Dctennining the large ofsample sia is hig}ly contexr dependent- In genemt, the
larger the din)ension of paramel€r, the larger sample size must be to obtain a given deeree of
approximatio.. In nan! cases ofNN application, the data set is randomly split inio two
mnrually exclusive subs€rs, i.e. lraining and lesriog sets. The firsl is used for model building,
\vhile the second is used ro assess lhe pe.formanca (sefleralization) ofrhe model- Both training
and resting sets are the sarne size. In this paper, frve difTerent datn panirioning is utilized to rest
vheih€r the prcdiciion ability of NN is affecred by rb€ number ofobservalion in taining set.
The purpose oflhis papcl is to cvduate rhe effect of mlio betwe€n rraining nnd t€sring s€ts ro
the ftisclassificalion rate in neu.al networks (NN) model. An e pirical sludy has been done by
using Fishefs
jris
data. The results show ihat the hrhclassification ratc decrease when the
number oftraining set increase. Model with 2 hidden neuron obtains minimum error when the
ratio oftraining set is 20%. Wher$s model with I hidden neuron yieldq rhc minirnum eror ar
th e .atio of rrain ing set 400/0, 50o/a, 600/0 and 80d/o |
| first_indexed | 2024-03-05T23:19:50Z |
| format | Article |
| id | oai:generic.eprints.org:32917 |
| institution | Universiti Gadjah Mada |
| language | English |
| last_indexed | 2024-03-13T19:12:14Z |
| publishDate | 2006 |
| record_format | dspace |
| spelling | oai:generic.eprints.org:329172016-03-07T04:31:59Z https://repository.ugm.ac.id/32917/ TIIE EFFECT OF RATIO BETWEEN TRAINING AI'iD TESTING SETS IN MODEL SELECTION FOR NEURAL NETWORKS CLASSIFICATION rezeki, sri Subanar, Subanar Suryo, Guritno Statistics Dctennining the large ofsample sia is hig}ly contexr dependent- In genemt, the larger the din)ension of paramel€r, the larger sample size must be to obtain a given deeree of approximatio.. In nan! cases ofNN application, the data set is randomly split inio two mnrually exclusive subs€rs, i.e. lraining and lesriog sets. The firsl is used for model building, \vhile the second is used ro assess lhe pe.formanca (sefleralization) ofrhe model- Both training and resting sets are the sarne size. In this paper, frve difTerent datn panirioning is utilized to rest vheih€r the prcdiciion ability of NN is affecred by rb€ number ofobservalion in taining set. The purpose oflhis papcl is to cvduate rhe effect of mlio betwe€n rraining nnd t€sring s€ts ro the ftisclassificalion rate in neu.al networks (NN) model. An e pirical sludy has been done by using Fishefs jris data. The results show ihat the hrhclassification ratc decrease when the number oftraining set increase. Model with 2 hidden neuron obtains minimum error when the ratio oftraining set is 20%. Wher$s model with I hidden neuron yieldq rhc minirnum eror ar th e .atio of rrain ing set 400/0, 50o/a, 600/0 and 80d/o 2006-12 Article PeerReviewed application/pdf en https://repository.ugm.ac.id/32917/1/2.pdf rezeki, sri and Subanar, Subanar and Suryo, Guritno (2006) TIIE EFFECT OF RATIO BETWEEN TRAINING AI'iD TESTING SETS IN MODEL SELECTION FOR NEURAL NETWORKS CLASSIFICATION. artikel, 2 (2). pp. 17-29. ISSN 1693 5098 |
| spellingShingle | Statistics rezeki, sri Subanar, Subanar Suryo, Guritno TIIE EFFECT OF RATIO BETWEEN TRAINING AI'iD TESTING SETS IN MODEL SELECTION FOR NEURAL NETWORKS CLASSIFICATION |
| title | TIIE EFFECT OF RATIO BETWEEN TRAINING AI'iD TESTING
SETS IN MODEL SELECTION FOR NEURAL NETWORKS
CLASSIFICATION |
| title_full | TIIE EFFECT OF RATIO BETWEEN TRAINING AI'iD TESTING
SETS IN MODEL SELECTION FOR NEURAL NETWORKS
CLASSIFICATION |
| title_fullStr | TIIE EFFECT OF RATIO BETWEEN TRAINING AI'iD TESTING
SETS IN MODEL SELECTION FOR NEURAL NETWORKS
CLASSIFICATION |
| title_full_unstemmed | TIIE EFFECT OF RATIO BETWEEN TRAINING AI'iD TESTING
SETS IN MODEL SELECTION FOR NEURAL NETWORKS
CLASSIFICATION |
| title_short | TIIE EFFECT OF RATIO BETWEEN TRAINING AI'iD TESTING
SETS IN MODEL SELECTION FOR NEURAL NETWORKS
CLASSIFICATION |
| title_sort | tiie effect of ratio between training ai id testing sets in model selection for neural networks classification |
| topic | Statistics |
| url | https://repository.ugm.ac.id/32917/1/2.pdf |
| work_keys_str_mv | AT rezekisri tiieeffectofratiobetweentrainingaiidtestingsetsinmodelselectionforneuralnetworksclassification AT subanarsubanar tiieeffectofratiobetweentrainingaiidtestingsetsinmodelselectionforneuralnetworksclassification AT suryoguritno tiieeffectofratiobetweentrainingaiidtestingsetsinmodelselectionforneuralnetworksclassification |