Boring Berlin Scientist

2021-09-08 13:00:01 Best Practices on Recommendation Systems by Microsoft

- Github Open / Comment

2021-09-06 13:00:16 Applications of Graph Neural Networks Open / Comment

2021-08-16 13:00:09 Netron - the crossplatform tool for visualizing deep learning models:

- Github Open / Comment

2021-08-13 13:00:04 The repo with the intuitive explanations, clean code and visuals about ML:

- GitHub Open / Comment

2021-08-11 13:00:04 The deep fake library for face swapping:

- GitHub Open / Comment

2021-08-09 13:00:03 The description of the PyTorch implementation of the paper Graph Attention Networks:

- The original post Open / Comment

2021-08-08 13:00:08 Recommendations with Bandit models from TF-agents library:

- The original blog post
- GitHub Open / Comment

2021-08-07 11:23:22 The introduction article about the new Deep Mind's multipurpose architecture Perceiver IO:

- The Original Blog Post
- The GitHub Open / Comment

2021-06-13 14:13:36 Chinese researchers are very fond of doing extensive surveys of a particular sub-field of machine learning, listing the main works and the major breakthrough ideas. There are so many articles published every day, and it is impossible to read everything. Therefore, such reviews are valuable (if they are well written, of course, which is quite rare).

Recently there was a very good paper reviewing various variants of Transformers with a focus on language modeling (NLP). This is a must-read for anyone getting into the world of NLP and interested in Transformers. The paper discusses the basic principles of self-attention and such details of modern variants of Transformers as architecture modifications, pre-training, and various applications.

Paper: A Survey of Transformers. Open / Comment

2021-02-23 14:00:03 data-describe is a Python toolkit for Exploratory Data Analysis (EDA) Open / Comment