论文信息 - Virtual sample generation using a population of networks

Virtual sample generation using a population of networks

Multilayer perceptrons have been shown to approximate any continuous functions with a desired precision. With insufficient training samples, however, the network can not learn the function properly and popular model selection methods such as cross validation can not be used. We propose a scheme to generate virtual samples using a population of networks. They are applied to regression problems and are shown to improve generalization and to solve the model selection problem at the same time.

Sungzoon Cho | Min Jang | Sungjune Chang

[1] David A. Cohn,et al. Active Learning with Statistical Models , 1996, NIPS.

[2] M. V. Rossum,et al. In Neural Computation , 2022 .

[3] Y. Chien,et al. Pattern classification and scene analysis , 1974 .

[4] A. Bandura. Social learning theory , 1977 .

[5] Peter L. Bartlett,et al. Vapnik-Chervonenkis Dimension Bounds for Two- and Three-Layer Networks , 1993, Neural Computation.

[6] Yaser S. Abu-Mostafa,et al. Hints , 2018, Neural Computation.

[7] Guozhong An,et al. The Effects of Adding Noise During Backpropagation Training on a Generalization Performance , 1996, Neural Computation.

[8] Sungzoon Cho,et al. Evolution of neural network training set through addition of virtual samples , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[9] Ken-ichi Funahashi,et al. On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.