arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.06886cs.NEcs.AIcs.LG
收藏

基于网络结构分布估计的神经网络结构搜索

Neural Architecture Search by Estimation of Network Structure Distributions

Tampere University(坦佩雷大学);Finnish Environment Institute(芬兰环境研究所)

Anton Muravev, Jenni Raitoharju, Moncef Gabbouj

摘要:

深度学习的影响力在不同领域不断扩大,其新的应用无处不在。因此,神经网络设计的问题越来越重要,因为传统的经验方法正在达到其极限。从头开始手动设计网络架构在很大程度上依赖于试错,而使用现有的预训练模型可能会引入冗余或漏洞。自动化神经架构设计能够克服这些问题,但最成功的算法是在设计空间明显受限的情况下进行的,假设目标网络由相同的重复块组成。虽然这种方法允许更快的搜索,但它是以表达能力为代价的。相反,我们提出了一个替代的概率表示的整个神经网络结构的层类型之间的独立性的假设下。我们的概率矩阵相当于模型的总体,但允许发现结构的不规则性,同时易于解释和分析。我们构建了一个架构搜索算法,灵感来自估计的分布算法,利用这种表示。概率矩阵通过反复对架构进行采样并评估相应的网络,同时逐渐增加模型深度,从而生成高性能模型。我们的算法被证明可以发现不规则的模型,这些模型不能通过块来表达,但在准确性和计算成本方面都具有竞争力,同时不利用复杂的递归或高级训练技术,并且保持概念简单和高度可扩展。

英文摘要:

The influence of deep learning is continuously expanding across different domains, and its new applications are ubiquitous. The question of neural network design thus increases in importance, as traditional empirical approaches are reaching their limits. Manual design of network architectures from scratch relies heavily on trial and error, while using existing pretrained models can introduce redundancies or vulnerabilities. Automated neural architecture design is able to overcome these problems, but the most successful algorithms operate on significantly constrained design spaces, assuming the target network to consist of identical repeating blocks. While such approach allows for faster search, it does so at the cost of expressivity. We instead propose an alternative probabilistic representation of a whole neural network structure under the assumption of independence between layer types. Our matrix of probabilities is equivalent to the population of models, but allows for discovery of structural irregularities, while being simple to interpret and analyze. We construct an architecture search algorithm, inspired by the estimation of distribution algorithms, to take advantage of this representation. The probability matrix is tuned towards generating high-performance models by repeatedly sampling the architectures and evaluating the corresponding networks, while gradually increasing the model depth. Our algorithm is shown to discover non-regular models which cannot be expressed via blocks, but are competitive both in accuracy and computational cost, while not utilizing complex dataflows or advanced training techniques, as well as remaining conceptually simple and highly extensible.

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。

↑