Researchers propose dual-system AI learning architecture inspired by animal cognition; combines observation and active behavior with meta-control signals to achieve autonomous learning in dynamic environments.

Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science

View PDF HTML (experimental) Abstract:We critically examine the limitations of current AI models in achieving autonomous learning and propose a learning architecture inspired by human and animal cognition. The proposed framework integrates learning from observation (System A) and learning from active behavior (System B) while flexibly switching between these learning modes as a function of internally generated meta-control signals (System M). We discuss how this could be built by taking inspirat...