Special Notes on Mar. 4, 2019

Weekly notes. In this note we are mainly learning "Solving ill-posed inverse problems using iterative deep neural networks".

Special Notes on Feb. 27, 2019

Weekly notes. In this note we are mainly learning "NETT: Solving Inverse Problems with Deep Neural Networks".

Guide book for Tensorflow

[Chinese] a guide book for starters who want to learn Tensorflow.

Notes from Jan. 29, 2019 to Feb. 15, 2019

A collection for other's researches about inverse problem. This article is an introduction and also a categorization.

Special Notes on Aug. 24, 2018

A short discussion about the derivation of LMA from the function expansion view.

Special Notes on Aug. 13, 2018

A collection of the discussions about the deep-learning implementation of proximal learning, and conventional inverse algorithms like ISTA and AMP.

Notes on Jul. 20, 2018

A collection for abstracts of those papers related to inverse problem enhanced by deep learning. This is the part I.

Tensorflow Inspection for FWM Curves 180602

[PRIVATE] Using the forward model by tensorflow-python-api. We would discuss about how to use data driven methods and model driven methods here.

Special Notes on Jun. 05, 2018

The note is just for one important article, "Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization", Part I.

Notes on May 26, 2018

The note for weekly report on May 26, 2018.

Notes on May 18, 2018

The note for weekly report on May 26, 2018.

Deep Learning for AGT

[PRIVATE] DeepNet projects for AGT (Advanced Geophysical Technology) and 2018 SEG (Society of Exploration Geophysicists) conference. Now it contains a denoise project and a FWI prediction project.

Real-time Shaker Video Analysis for Shell Project

[PRIVATE] This is a mpegprocessor for Shell Project which is used to analyzing the video of a shale shaker. Since it has not been published, now it is not avaliable for reaching the project page.

Deep Learning Utilities

A C++ based tool collection for enhancing the pre-processing and IO of deep learning.

Get Back

Get back to the higher stage contents.