反向传播进化
Backprop Evolution
摘要：
反向传播算法是深度学习的基石。尽管它的重要性，一些变化的算法已被尝试。这项工作提出了一种方法来发现新的变化的反向传播方程。我们使用一个特定领域的语言来描述更新方程作为一个原始函数的列表。一种基于进化的方法被用来发现新的传播规则，最大限度地提高泛化性能后，几个时代的训练。我们发现几个更新方程，可以训练更快，训练时间短，比标准的反向传播，并执行类似的标准反向传播收敛。
英文摘要：
The back-propagation algorithm is the cornerstone of deep learning. Despite its importance, few variations of the algorithm have been attempted. This work presents an approach to discover new variations of the back-propagation equation. We use a domain specific lan- guage to describe update equations as a list of primitive functions. An evolution-based method is used to discover new propagation rules that maximize the generalization per- formance after a few epochs of training. We find several update equations that can train faster with short training times than standard back-propagation, and perform similar as standard back-propagation at convergence.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
