a new telegram channel where will post about #explainableai (#XAI for short): t.me/s/explainablea…
there are now many useful libraries available for doing #explainability of #AI models: SHAP, LIME, partial dependence plots PDP. And also the "classical" feature importance.
Profile on devrant, which is a cool webpage with interesting comments about machine learning: devrant.com/users/aidatasc…
Machine learning notes will be published on hackmd.io/@bestniches
on different topics -> ensemble methods, content-based and collaborative filtering articles, sentiment analysis, etc.
Deep learning generated images on ello.co/datascientist1
Style transfer is a cool technique to transfer "style" from reference image to your input image to generate one which is the same but with applied style