The field of meta-learning seeks to improve the ability of today's machine learning systems to adapt efficiently to small amounts of data. Typically this is accomplished by training a system with a parametrized update rule to improve a task-relevant objective based on supervision or a reward function. However, in many domains of practical interest, task data is unlabeled, or reward functions are unavailable. In this paper we introduce a new approach to address the more general problem of generative meta-learning, which we argue is an important prerequisite for obtaining human-level cognitive flexibility in artificial agents, and can benefit many practical applications along the way. Our contribution leverages the AEVB framework and mean-field variational Bayes, and creates fast-adapting latent-space generative models. At the heart of our contribution is a new result, showing that for a broad class of deep generative latent variable models, the relevant VB updates do not depend on any generative neural network. The theoretical merits of our approach are reflected in empirical experiments.
翻译:元学习领域力求提高当今机器学习系统的能力,以便有效地适应少量数据。通常,通过培训一个具有平衡更新规则的系统,在监督或奖励功能的基础上改进与任务有关的目标,来实现这一目标。然而,在许多实际感兴趣的领域,任务数据没有标签,或没有奖励功能。在本文件中,我们引入了一种新办法,以解决基因化元学习这一更为普遍的问题,我们认为,这是在人工剂中获得人的水平认知灵活性的重要先决条件,并能够使许多实际应用不断受益。我们的贡献利用了AEVB框架和平均场变异海湾,创造了快速适应的潜空基因化模型。我们贡献的核心是一个新结果,表明对于一系列深层基因化潜在变异模型来说,相关的VB更新并不取决于任何基因化神经网络。我们方法的理论优点反映在实验中。