Learning representations that generalize systematically

深度学习算法是最近几乎所有围绕人工智能的兴奋背后的驱动力。尽管如此，有明显的迹象表明，这些方法的性能在实验室条件之外会恶化。我制定了一个研究计划，以开发学习表示法，将学习到的关联概括到训练分布之外，我们称之为系统概括。为此，我们探索了两大类学习算法：(1)自监督学习方法和(2)迭代学习。我们还建议将系统概括的概念在数学上形式化，并从理论上分析实现它的有前途的途径。

Deep learning algorithms are the driving force behind virtually all recent excitement around AI. Despite this, there are clear signs that the performance of these methods deteriorates outside of laboratory conditions. I set out a research program to develop learning representations that generalize learned associations beyond the training distribution, which we refer to as systematic generalization. To this end, we explore two broad categories of learning algorithms: (1) self-supervised learning methods and (2) iterated learning. We also propose to mathematically formalize the notion of systematic generalization and theoretically analyze promising avenues to achieve it.