Abstract | ||
---|---|---|
Ensemble learning system could lessen the degree of overfitting that often appear in the supervised learning process for a single learning model. However, overfitting had still been observed in negative correlation learning that is an ensemble learning method with correlation-based penalty. Two constraints were introduced into negative correlation learning in order to conquer such overfitting. One is the lower bound of error rate (LBER). The other is the upper bound of error output (UBEO). With LBER and UBEO, negative correlation learning will selectively learn the data points. After the performance becomes better than LBER, those unlearned data points with the error output larger than UBEO would not be learned anymore in negative correlation learning. This paper presented the experimental results to explain how these two constraints would affect the performance of negative correlation learning. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/DASC.2014.69 | DASC |
Keywords | Field | DocType |
overfitting,supervised learning,single learning model,neural networks,correlation-based penalty,lber,unlearned data points,negative correlation learning,learning (artificial intelligence),supervised learning process,ensemble learning, supervised learning, neural networks,lower bound of error rate,ensemble learning,ensemble learning system,ubeo,neural nets,upper bound of error output,correlation,training data | Instance-based learning,Stability (learning theory),Semi-supervised learning,Probably approximately correct learning,Computer science,Supervised learning,Unsupervised learning,Artificial intelligence,Overfitting,Ensemble learning,Machine learning | Conference |
Citations | PageRank | References |
0 | 0.34 | 7 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yong Liu | 1 | 2526 | 265.08 |
Qiangfu Zhao | 2 | 214 | 62.36 |
Yan Pei | 3 | 125 | 22.89 |