A Short Survey of Systematic Generalization
It provides a background resource for researchers working on systematic generalization, but it is incremental as it primarily surveys existing work without introducing new methods or results.
This survey paper organizes and summarizes the history and recent improvements in systematic generalization across machine learning, covering definitions, classicist and connectionist approaches, and key problems like variable binding and causality in fields such as language, vision, and VQA.
This survey includes systematic generalization and a history of how machine learning addresses it. We aim to summarize and organize the related information of both conventional and recent improvements. We first look at the definition of systematic generalization, then introduce Classicist and Connectionist. We then discuss different types of Connectionists and how they approach the generalization. Two crucial problems of variable binding and causality are discussed. We look into systematic generalization in language, vision, and VQA fields. Recent improvements from different aspects are discussed. Systematic generalization has a long history in artificial intelligence. We could cover only a small portion of many contributions. We hope this paper provides a background and is beneficial for discoveries in future work.