Learning by a population of perceptrons
暂无分享,去创建一个
We study learning from example~ by a population of neural networks. A group of single layer perceptions with discrete weights learn from a two-layer neural network. Each member is trained independently from the same or independent example sets. They vote for an answer of new problems. We calculate the generalization performance of the group decision by majority vote. The generalization error decreases to a minimum at a certain number of examples and increases again.
[1] M. V. Rossum,et al. In Neural Computation , 2022 .
[2] H. Sebastian Seung,et al. Learning from a Population of Hypotheses , 1993, COLT '93.
[3] Jong-Hoon Oh,et al. Generalization in partially connected layered neural networks , 1994, COLT '94.