This is a Matlab tutorial written in Chinese.
大规模分布式系统课上的Final Project需要作Word Vec的可视化，预期做成类似TensorFlow Embedding Projector的效果。前端使用Flask，可视化工具在看了d3.js、echarts和pyecharts之后还是选定了pyecharts。虽然以前也有用过，但这次用又有新的感（踩）悟（坑），特此纪念。
This is a note taken in Chinese recording my preparation for implementing final project of data science course Data Visualization. We aim to design a 3D human face free form deformation system. I’ll concentrate on implementing codes related to VTK package and design the GUI.
The Visualization Toolkit (VTK) is an open-source, freely available software system for 3D computer graphics, image processing, and visualization. It’s a little bit difficult to learn how to use it since its document is not completed. I read some blogs as well as technical books, and take down some notes here.
I will be a research assistant under the guidance of Prof.Xiang Ren at USC next term, hence I’m reading some related papers and taking some notes for preparation.
I’ll mainly work on a relation extraction task that incorporates both text and knowledge graph. The core of the project is to generate meaningful “paths/rules” between entities on the knowledge graph to “explain” the model prediction. This is particularly important when we work on biomedical domain or product domain, etc.
I’ve read some papers on relation extraction already (you can read my blogs here), so I’m reading some context on graph embedding and knowledge graph completion this time.
This is a note about implementing the final project of my Artificial Intelligence course. The scope of this project is develop an AI agent for Gomoku.
Gomoku, also know as five-in-a-row, is a strategy board game which is traditionally played with Go pieces on a go board with 15 × 15 intersections. The rules for Gomoku are similar to Go, where two players place stones alternatively on the intersections of the board. The winner is the first player to get 5 of their stones in a row, either vertically, horizontally or diagonally.
Me and my partners (Xisen, Zhankui) are working on conversation generation models with extra emotional information. I use this blog to record some implementation details and take notes during paper reading process.
Also, I followed some ideas from several papers to form our own paper’s introduction and related works.