Interactive Continual Learning: Fast and Slow Thinking

arXiv:2403.02628v1 Announce Type: cross
Abstract: Advanced life forms, sustained by the synergistic interaction of neural cognitive mechanisms, continually acquire and transfer knowledge throughout their lifespan. In contrast, contemporary machine learning paradigms exhibit limitations in emulating the facets of continual learning (CL). Nonetheless, the emergence of large language models (LLMs) presents promising avenues for realizing CL via interactions with these models. Drawing on Complementary Learning System theory, this paper presents a novel Interactive Continual Learning (ICL) framework, enabled by collaborative interactions …

abstract advanced arxiv cognitive continual contrast cs.cv cs.lg emergence forms interactive knowledge language language models large language large language models life limitations llms machine machine learning thinking transfer type