Open the address of official website and search for the paper you want in the upper left corner.

The artifact with code can effectively retrieve the best information in various fields of AI. Only by reading the paper and further reading the code can we thoroughly understand the ideas and skills of the paper.

Paperwithcode website corresponds the latest machine learning papers on ArXiv with the codes on GitHub (TensorFlow/Pytorch/mxnet/etc.). ).

According to the website developer, it contains 966 machine learning tasks, 565,438+05 evaluation leaderboards (and the best results at present), 8,625 papers (with source code) and 704 data sets, and it is constantly updated. Paperwithcode website covers a wide range of machine learning tasks, including computer vision, natural language processing and so on.

With the development of deep learning, there are more and more researches on using deep learning to solve problems in related communication fields. As a graduate student majoring in communication, it will be very difficult to get started and go deep into a new direction if there is no code accumulation in the relevant direction in the laboratory. At the same time, most papers in the field of communication will not provide open source code, so it is difficult to study replicability.

Summarized as follows:

Communication papers based on deep learning have grown rapidly in recent years. In some papers, it is obvious that the author is more open-source spirit. This project focuses on combing the application of deep learning in communication, and publishing related source code papers. Due to personal concerns and limited energy, this list will not be so complete.

If you know some related open source papers, but they are not in this list, you are very welcome to add them and contribute to the community.