Metabolic cost as an organizing principle for cooperative learning
This addresses the problem of understanding neural cooperation for researchers in neuroscience and AI, offering a potential organizing principle for neural codes and cooperative systems, though it is incremental in building on existing decision-making studies.
The paper tackles how neurons can cooperate for learning by using metabolic cost as a constraint, showing that this aligns action information with expected reward and improves accuracy and robustness in distributed learning, with theoretical findings confirmed by two implementations.
This paper investigates how neurons can use metabolic cost to facilitate learning at a population level. Although decision-making by individual neurons has been extensively studied, questions regarding how neurons should behave to cooperate effectively remain largely unaddressed. Under assumptions that capture a few basic features of cortical neurons, we show that constraining reward maximization by metabolic cost aligns the information content of actions with their expected reward. Thus, metabolic cost provides a mechanism whereby neurons encode expected reward into their outputs. Further, aside from reducing energy expenditures, imposing a tight metabolic constraint also increases the accuracy of empirical estimates of rewards, increasing the robustness of distributed learning. Finally, we present two implementations of metabolically constrained learning that confirm our theoretical finding. These results suggest that metabolic cost may be an organizing principle underlying the neural code, and may also provide a useful guide to the design and analysis of other cooperating populations.