自动机器学习（AutoML）是将机器学习应用于实际问题的过程的自动化过程。AutoML涵盖了从原始数据集到可部署的机器学习模型的完整管道。提出将AutoML作为基于人工智能的解决方案来应对不断增长的应用机器学习的挑战。 AutoML的高度自动化允许非专家使用机器学习模型和技术，而无需首先成为该领域的专家。 从机器学习角度讲，AutoML 可以看作是一个在给定数据和任务上学习和泛化能力非常强大的系统。但是它强调必须非常容易使用；从自动化角度讲，AutoML 则可以看作是设计一系列高级的控制系统去操作机器学习模型，使得模型可以自动化地学习到合适的参数和配置而无需人工干预。
VIP内容
自动机器学习
·
深度学习让机器可以从大量的数据中学习经验并加以应用，已经在图像分类、序列标注等多个任务上取得了惊人的成果。但是，这一过程需要大量的人工干预：特征提取、模型选择、参数调节等，既费时又费力。
所以专家们自然而然想到了引入自动化让机器自己“学习如何学习”。然而机器学习的自动化离不开几个关键难题：教授什么知识和配备什么工具？在哪一部分实现自动化？自动化训练如何保证稳定的效果？如何在最短时间内找到又简单又高效的方案？
论文指出，当前的自动机器学习多是在整个流程中的某个或某几个独立分段实现自动化，这种 “半自动” 让搜索自然受限于 “次优” 并导致最终结果的偏差。而且搜索空间往往“精心设计”，与自动学习的初衷相违背，实际落地时也易出现过拟合的情况。很显然，自动机器学习需要对网络结构有更高一级的理解能力。
首先，论文的作者提出了基于终身知识锚点的进化算法。而其中极富创新性的全自动机器学习框架，首次打破了现有自动机器学习中各搜索空间的独立设计，并使用数据集知识锚点加进化算法来加速搜索，解决了在超大空间搜索最优方案的设计难题。
承袭现有的终身学习与元学习思想，该框架中的知识锚点使用了全新的元特征和概率抽样方法，缓解了搜索过程中的过拟合。不仅如此，框架还实现了全流程自动化，极大降低了机器学习应用门槛。用户只需根据提示进行操作，无须了解算法和代码，时间成本很低。
成为VIP会员查看完整内容
Evolving Fully Automated Machine Learning via Life-Long Knowledge Anchors
热门内容
最新内容
AutoML systems are currently rising in popularity, as they can build powerful models without human oversight. They often combine techniques from many different sub-fields of machine learning in order to find a model or set of models that optimize a user-supplied criterion, such as predictive performance. The ultimate goal of such systems is to reduce the amount of time spent on menial tasks, or tasks that can be solved better by algorithms while leaving decisions that require human intelligence to the end-user. In recent years, the importance of other criteria, such as fairness and interpretability, and many others have become more and more apparent. Current AutoML frameworks either do not allow to optimize such secondary criteria or only do so by limiting the system's choice of models and preprocessing steps. We propose to optimize additional criteria defined by the user directly to guide the search towards an optimal machine learning pipeline. In order to demonstrate the need and usefulness of our approach, we provide a simple multi-criteria AutoML system and showcase an exemplary application.
最新论文
AutoML systems are currently rising in popularity, as they can build powerful models without human oversight. They often combine techniques from many different sub-fields of machine learning in order to find a model or set of models that optimize a user-supplied criterion, such as predictive performance. The ultimate goal of such systems is to reduce the amount of time spent on menial tasks, or tasks that can be solved better by algorithms while leaving decisions that require human intelligence to the end-user. In recent years, the importance of other criteria, such as fairness and interpretability, and many others have become more and more apparent. Current AutoML frameworks either do not allow to optimize such secondary criteria or only do so by limiting the system's choice of models and preprocessing steps. We propose to optimize additional criteria defined by the user directly to guide the search towards an optimal machine learning pipeline. In order to demonstrate the need and usefulness of our approach, we provide a simple multi-criteria AutoML system and showcase an exemplary application.
