Ensembling neural networks: Many could be better than all

Neural network ensemble is a learning paradigm where many neural networks are jointly used to solve a problem. In this paper, the relationship between the ensemble and its component neural networks is analyzed from the context of both regression and classification, which reveals that it may be better to ensemble many instead of all of the neural networks at hand. This result is interesting because at present, most approaches ensemble all the available neural networks for prediction. Then, in order to show that the appropriate neural networks for composing an ensemble can be effectively selected from a set of available neural networks, an approach named GASEN is presented. GASEN trains a number of neural networks at first. Then it assigns random weights to those networks and employs genetic algorithm to evolve the weights so that they can characterize to some extent the fitness of the neural networks in constituting an ensemble. Finally it selects some neural networks based on the evol...

• Type: Journal
• Year: 2002
• Where: AI
• Authors: Zhi-Hua Zhou, Jianxin Wu, Wei Tang
• Keywords: AI 2002, Artificial Intelligence, Available Neural Networks, Neural Network, Neural Network Ensemble