论文标题
合并神经网络
Merging of neural networks
论文作者
论文摘要
我们提出了一个简单的方案，以合并两个神经网络，这些神经网络训练有不同的启动初始化，成一个与原始大小相同的神经网络。我们通过仔细从每个输入网络中选择渠道来做到这一点。在尝试多个起始种子以避免不幸的种子之后，我们的过程可以用作最终确定步骤。我们还表明，培训两个网络并合并它们会导致性能比在很长一段时间内训练单个网络更好。 可用性：https：//github.com/fmfi-compbio/neural-network-merging
We propose a simple scheme for merging two neural networks trained with different starting initialization into a single one with the same size as the original ones. We do this by carefully selecting channels from each input network. Our procedure might be used as a finalization step after one tries multiple starting seeds to avoid an unlucky one. We also show that training two networks and merging them leads to better performance than training a single network for an extended period of time. Availability: https://github.com/fmfi-compbio/neural-network-merging
