Learning in LIDA
Sean Kugele, S. Franklin
Cognitive Systems Research November 21, 2020 DOI: 10.1016/j.cogsys.2020.11.001 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Theoretical or philosophical paper Peer reviewed |
|---|---|
| Key points | Argues that learning in LIDA is constrained by the Conscious Learning Hypothesis from Global Workspace Theory, which holds that all significant learning requires consciousness. The authors synthesize conceptual work on LIDA's learning mechanisms, examine what must be innate versus learned and the nature of its representations, and propose a roadmap for bridging the conceptual model and its implementations. |
Abstract
Abstract LIDA is a systems-level, biologically-inspired cognitive architecture. More than a decade of research on LIDA has seen much conceptual work on its learning mechanisms, and resulted in a set of conceptual commitments that constrain those mechanisms; perhaps the most essential of these constraints is the Conscious Learning Hypothesis from Global Workspace Theory, which asserts that all significant learning requires consciousness. Despite these successes, many conceptual challenges remain, and bridging the divide between LIDA’s conceptual model and its implementations has been challenging. The contributions of this paper are threefold: We present a detailed survey of learning in LIDA, during which we clarify, elaborate on, and synthesize together ideas from numerous papers, using updated terminology that reflects the continuing evolution of LIDA. We explore foundational issues in learning, such as, “What must be innate or built-in?” versus “What can be learned?”, the nature of LIDA’s representations, and the relationship between the LIDA conceptual model and its computational realizations. Finally, we provide a roadmap for future work. We believe that this paper will direct and catalyze our research endeavors, and provide a thorough introduction to the conceptual foundations of LIDA’s learning mechanisms that will be useful to anyone that would like a deeper understanding of LIDA or for those that plan to implement LIDA-based agents.