The invention relates to a machine learnable system with normalizing flow. Some embodiments are directed to a machine learnable system (110). A conditional normalizing flow function maps a latent representation (z) to a base point (e=f(z,c)) in a base space (E) conditional on conditioning data (c). The conditional normalizing flow function is a machine learnable function and trained on a set of training pairs.
具有标准化流的机器可学习系统。一些实施例针对机器可学习系统(110)。条件标准化流函数以条件作用数据(c)为条件将潜在表示(z)映射到基础空间(E)中的基础点()。条件标准化流函数是机器可学习函数,并且在训练对的集合上被训练。
A MACHINE LEARNABLE SYSTEM WITH NORMALIZING FLOW
具有标准化流的机器可学习系统
2021-01-19
Patent
Electronic Resource
Chinese
A MACHINE LEARNABLE SYSTEM WITH CONDITIONAL NORMALIZING FLOW
European Patent Office | 2021
|