Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science
This addresses the challenge of building more adaptive AI systems for real-world applications, but it appears incremental as it builds on existing cognitive science concepts without demonstrated breakthroughs.
The paper tackles the problem of current AI models lacking autonomous learning capabilities by proposing a cognitive science-inspired architecture that integrates observation-based and behavior-based learning with meta-control switching, though no concrete performance numbers are provided.
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 inspiration on how organisms adapt to real-world, dynamic environments across evolutionary and developmental timescales.