Normalising Flows — The Model That Prices Every Point in the Plane
中文摘要
归一化流通过可逆变换将简单分布映射为复杂分布，从而实现对空间中任意点概率密度的精确估计。
English Summary
Normalizing flows use invertible transformations to map simple distributions to complex ones, enabling precise probability density estimation for any point in space.
原文节选
Algorithms in Python — Deep Learning Architectures, Part 10 Continue reading on Medium »