We present Deep-n-Cheap -- an open-source AutoML framework to search for deep learning models. This search includes both architecture and training hyperparameters, and supports convolutional neural networks and multi-layer perceptrons. Our framework is targeted for deployment on both benchmark and custom datasets, and as a result, offers a greater degree of search space customizability as compared to a more limited search over only pre-existing models from literature. We also introduce the technique of 'search transfer', which demonstrates the generalization capabilities of the models found by our framework to multiple datasets. Deep-n-Cheap includes a user-customizable complexity penalty which trades off performance with training time or number of parameters. Specifically, our framework results in models offering performance comparable to state-of-the-art while taking 1-2 orders of magnitude less time to train than models from other AutoML and model search frameworks. Additionally, this work investigates and develops various insights regarding the search process. In particular, we show the superiority of a greedy strategy and justify our choice of Bayesian optimization as the primary search methodology over random / grid search.
翻译:我们展示了深海同步(Deep-n-cheap) -- -- 一个用于寻找深学习模型的开放源码自动移动框架。这种搜索包括建筑和训练超参数,支持进化神经网络和多层光谱。我们的框架针对基准和自定义数据集进行部署,因此,与仅针对文献中原有模型的更有限的搜索相比,提供了更大程度的搜索空间自定义性,而相比之下,仅针对文献中的原有模型,我们还引入了“搜索转移”技术,这显示了我们框架发现的模型对多个数据集的普遍化能力。深n-Cheap包括一个用户可定制的复杂处罚,用培训时间或参数数来交换功能。具体地说,我们的框架成果是提供与最新数据相仿的性能模型,同时比其他自动流和模型搜索框架的模型少1-2级培训时间。此外,这项工作还调查并发展了有关搜索过程的各种见解。我们特别展示了贪婪战略的优越性,并证明我们选择Bayesian优化为主要搜索方法的理由,而不是随机/电网格搜索方法。