arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1608.07892stat.MLcs.LG
收藏

时间约束下循环神经网络结构的优化

Optimizing Recurrent Neural Networks Architectures under Time Constraints

Junqi Jin, Ziang Yan, Kun Fu, Nan Jiang, Changshui Zhang

摘要:

递归神经网络(RNN)的结构是影响其性能的关键因素。我们提出了算法,以优化隐藏的大小下运行时间的约束。我们将离散优化转化为一个子集选择问题。通过新颖的变换,使目标函数成为次模,约束成为超模。提出了一种带界的贪婪算法来求解变换后的问题。我们展示了变换如何影响边界。为了加快优化速度,提出了平衡探索和开发的代理函数。实验表明,我们的算法可以找到更准确的模型或更快的模型比手动调整的国家的最先进的和随机搜索。我们还使用我们的算法比较了流行的RNN架构。

英文摘要:

Recurrent neural network (RNN)'s architecture is a key factor influencing its performance. We propose algorithms to optimize hidden sizes under running time constraint. We convert the discrete optimization into a subset selection problem. By novel transformations, the objective function becomes submodular and constraint becomes supermodular. A greedy algorithm with bounds is suggested to solve the transformed problem. And we show how transformations influence the bounds. To speed up optimization, surrogate functions are proposed which balance exploration and exploitation. Experiments show that our algorithms can find more accurate models or faster models than manually tuned state-of-the-art and random search. We also compare popular RNN architectures using our algorithms.

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。

↑