大脑发育决定神经架构搜索的能量约束:关于优化策略的跨学科洞见
Brain development dictates energy constraints on neural architecture search: cross-disciplinary insights on optimization strategies
AI总结:
该研究从发育神经科学视角提出,大脑神经架构搜索以代谢优化而非预测误差为核心,为AI尤其是AGI的新型NAS设计及深度神经网络因果推理研究提供了新视角。
摘要:
当前的人工神经架构搜索(NAS)策略本质上都是以预测误差为优化目标的,这一点对各类AI功能而言普遍成立。从发育神经科学的视角,我提出证据表明,代谢优化而非预测误差优化的神经架构搜索(NAS)才是核心机制。支撑证据来自对人类大脑胶质-神经组织的最新研究,以及为该优化策略的功能表达提供数学基础的动态协调理论。这一发现对设计AI领域尤其是通用人工智能(AGI)中的新型NAS策略具有参考价值,还对深度神经网络的因果推理有额外启示。综上,发育神经科学的洞见为NAS及AI建模的基础假设提供了新视角。
英文摘要:
Present day artificial neural architecture search (NAS) strategies are essentially prediction-error-optimized. That holds true for AI functions in general. From the developmental neuroscience perspective, I present evidence for the central role of metabolically, rather than prediction-error-optimized neural architecture search (NAS). Supporting evidence is drawn from the latest insights into the glial-neural organization of the human brain and the dynamic coordination theory which provides a mathematical foundation for the functional expression of this optimization strategy. This is relevant to devising novel NAS strategies in AI, especially in AGI. Additional implications arise for causal reasoning from deep neural nets. Together, the insights from developmental neuroscience offer a new perspective on NAS and the foundational assumptions in AI modeling.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。