Pet peeve lately: complicated machine learning tutorials that end up with predictions that aren't a whole lot better than "prediction for timepoint x is equal to the value for timepoint x - 1." I mean... (From https://www.kaggle.com/ternaryrealm/lstm-time-series-explorations-with-keras )
Applied statistics masters student at Victoria University of Wellington. , #Cpp, and plenty else besides
The social network of the future: No ads, no corporate surveillance, ethical design, and decentralization! Own your data with Mastodon!