Meta Neural Coordination
This work addresses the problem of building autonomous, adaptive AI systems for researchers in machine learning and cognitive science, but it appears incremental as it builds on existing meta-learning and modular network concepts.
The paper tackles the challenge of enabling neural networks to adapt to new environments by proposing Meta Neural Coordination, which facilitates coordination among neural modules to represent multiple predictions and improve adaptability, though no concrete performance numbers are provided.
Meta-learning aims to develop algorithms that can learn from other learning algorithms to adapt to new and changing environments. This requires a model of how other learning algorithms operate and perform in different contexts, which is similar to representing and reasoning about mental states in the theory of mind. Furthermore, the problem of uncertainty in the predictions of conventional deep neural networks highlights the partial predictability of the world, requiring the representation of multiple predictions simultaneously. This is facilitated by coordination among neural modules, where different modules' beliefs and desires are attributed to others. The neural coordination among modular and decentralized neural networks is a fundamental prerequisite for building autonomous intelligence machines that can interact flexibly and adaptively. In this work, several pieces of evidence demonstrate a new avenue for tackling the problems above, termed Meta Neural Coordination. We discuss the potential advancements required to build biologically-inspired machine intelligence, drawing from both machine learning and cognitive science communities.