Learning representations that generalize systematically

学习系统概括的表征

• 批准号: CRC-2021-00162
• 负责人: Courville, Aaron
• 金额: $ 14.57万
• 依托单位: Université de Montréal
• 依托单位国家: 加拿大
• 项目类别: Canada Research Chairs
• 财政年份: 2022
• 资助国家: 加拿大
• 起止时间: 2022-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=750771
• 关键词: Learning; representations; generalize; systematically

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.

深度学习算法几乎是最近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恶化。我制定了一项研究计划，开发学习表征，将学习到的关联推广到训练分布之外，我们称之为系统推广。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。我们还建议在数学上形式化系统泛化的概念，并从理论上分析实现它的有希望的途径。