论文阅读-solving-ill-posed-inverse-problems-using-iterative-deep-neural-networks
Published:
论文阅读-Solving ill-posed inverse problems using iterative deep neural networks
inverse problem:
给定数据g,得到
通常方法:
是对f的先验信息的总结。
问题:需要计算量,需要显式地将S表达出来,正则化参数的选择
机器学习方法:
直接找一个pseudo-inverse:
监督性学习:
是分布,d是距离函数
非监督性:
as learning an optimiser for the variational rgularization
fully learned reconstruction :
通过data构建一个来逼近T的逆
缺点:需要大量的数据来满足各种的data manifold
sequential data and knowledge driven reconstruction:
损失函数:
找到最好的f使得损失最小。
假设右侧是Frechet differentiable,and convex
用普通的梯度下降法
用一个更新算子代替梯度部分:
用CNN拟合更新算子
加入一个memory ,用拟牛顿法
问题:这里是怎么来的?
用CNN,是3*3的卷积核
Deep Bayesian Inversion
a sampling based method using
a Wasserstein GAN with a novel mini-discriminator and a direct approach that trains
a neural network using a novel loss function.