arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.02425cs.NEcs.LG
收藏

基于随机误差采样的循环神经网络结构优化

Random Error Sampling-based Recurrent Neural Network Architecture Optimization

Universidad de Málaga(马拉加大学);Massachusetts Institute of Technology(麻省理工学院)

Andrés Camero, Jamal Toutouh, Enrique Alba

摘要:

递归神经网络擅长解决预测问题。然而,找到一个适合问题的网络是相当困难的,因为它们的性能受到其架构配置的强烈影响。自动架构优化方法有助于找到最合适的设计,但由于其高计算成本,它们没有被广泛采用。在这项工作中,我们介绍了基于随机误差采样的神经进化(RESN),一种进化算法,使用平均绝对误差随机采样,一种无需训练的方法来预测人工神经网络的预期性能,以优化网络的体系结构。我们经验验证我们的建议,三个预测问题,并比较我们的技术,以训练为基础的架构优化技术和神经进化方法。我们的研究结果表明,我们可以实现最先进的错误性能,我们减少了一半的时间需要执行优化。

英文摘要:

Recurrent neural networks are good at solving prediction problems. However, finding a network that suits a problem is quite hard because their performance is strongly affected by their architecture configuration. Automatic architecture optimization methods help to find the most suitable design, but they are not extensively adopted because of their high computational cost. In this work, we introduce the Random Error Sampling-based Neuroevolution (RESN), an evolutionary algorithm that uses the mean absolute error random sampling, a training-free approach to predict the expected performance of an artificial neural network, to optimize the architecture of a network. We empirically validate our proposal on three prediction problems, and compare our technique to training-based architecture optimization techniques and to neuroevolutionary approaches. Our findings show that we can achieve state-of-the-art error performance and that we reduce by half the time needed to perform the optimization.

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。

↑