Name
Abstract | ||
|---|---|---|
This paper proposes a hybrid negative correlation learning in which each individual neural network in an neural network ensemble would either learn a data point by negative correlation learning or learn to be different to the neural network ensemble. The implementation is through randomly splitting the training set into two subsets for each individual neural network in learning. On one subset of the training data, the individual neural network would be trained by negative correlation learning. On the other subset of the training data, the individual neural network would be trained to be different to the neural network ensemble. The purpose of such random splitting of the training data is to allow each individual neural network to build up its self-awareness of the learning direction on each given data point. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1109/ICInfA.2017.8078937 | 2017 IEEE International Conference on Information and Automation (ICIA) |
Keywords | Field | DocType |
hybrid negative correlation learning,training data,neural network ensembles learning | Competitive learning,Computer science,Recurrent neural network,Probabilistic neural network,Self-organizing map,Types of artificial neural networks,Time delay neural network,Artificial intelligence,Deep learning,Artificial neural network,Machine learning | Conference |
ISBN | Citations | PageRank |
978-1-5386-3155-3 | 1 | 0.41 |
References | Authors | |
5 | 1 | |