Gaussian Universality in Neural Network Dynamics with Generalized Structured Input Distributions
神经网络动力学中的高斯普遍性与广义结构输入分布
机构 * Department of Physics, Korea Advanced Institute of Science and Technology(韩国科学技术院物理系) ; Center of Complex Systems, Korea Advanced Institute of Science and Technology(韩国科学技术院复杂系统中心)
AI总结 本研究通过将输入建模为高斯混合分布,揭示了神经网络动力学在标准化后表现出高斯普遍性,从而增强了深度学习理论的理解。
Comments Accepted for Bridging the Gap Between Practice and Theory in Deep Learning (BGPT) Workshop at ICLR 2024, [v1] 23 pages, 16 figures