TL;DR基于 k 取胜神经元激活函数的合作集成神经网络(kWTA-ENN)是一种改进的集成方法,通过并行训练子网络并利用 k 取胜神经元激活函数,实现了专业化与知识共享的平衡,其在基准数据集上达到更好性能,例如 98.34%的 MNIST 测试准确率。
Abstract
ensembling is one approach that improves the performance of a neural network
by combining a number of independent neural networks, usually by either
averaging or summing up their individual outputs. We modify thi