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 2207.04467cs.LGcs.AIcs.NE
收藏

Noisy Heuristics NAS:一种基于网络形态的启发式神经结构搜索

Noisy Heuristics NAS: A Network Morphism based Neural Architecture Search using Heuristics

NAAMII;University College London(伦敦大学学院)

Suman Sapkota, Binod Bhattarai

摘要:

基于网络形态学的神经结构搜索(NAS)是最有效的方法之一,然而,知道在何处以及何时添加新的神经元或删除功能障碍的神经元通常留给黑盒强化学习模型。在本文中,我们提出了一个新的网络形态的NAS称为噪声启发式NAS,它使用人工开发的神经网络模型和生物神经元动力学的启发式学习。首先,我们随机添加新的神经元,并修剪掉一些,只选择最适合的神经元。其次,我们使用隐单元与输入输出连接数的关系来控制网络的层数。我们的方法可以在线增加或减少模型的容量或非线性,这是由用户指定的几个元参数。我们的方法既适用于玩具数据集,也适用于真实世界的数据集,如MNIST,CIFAR-10和CIFAR-100。性能与具有类似参数的手工设计架构ResNet-18相当。

英文摘要:

Network Morphism based Neural Architecture Search (NAS) is one of the most efficient methods, however, knowing where and when to add new neurons or remove dis-functional ones is generally left to black-box Reinforcement Learning models. In this paper, we present a new Network Morphism based NAS called Noisy Heuristics NAS which uses heuristics learned from manually developing neural network models and inspired by biological neuronal dynamics. Firstly, we add new neurons randomly and prune away some to select only the best fitting neurons. Secondly, we control the number of layers in the network using the relationship of hidden units to the number of input-output connections. Our method can increase or decrease the capacity or non-linearity of models online which is specified with a few meta-parameters by the user. Our method generalizes both on toy datasets and on real-world data sets such as MNIST, CIFAR-10, and CIFAR-100. The performance is comparable to the hand-engineered architecture ResNet-18 with the similar parameters.

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。

↑