Is it enough to report performance on a single dataset? Can we trust the reported improvement of new model architectures? We created 144 experiments for…
and

June 2022

The current limitations of Graph Neural Networks. We continue our two part series on ML on Graphs, by asking: could graphs replace other domain specific…
and
Why Machine Learning on Graphs could be the future of AI. Many researchers are doubling down on scaling models like GPT-3 on an ever bigger corpus of…
and

May 2021

Deep Reinforcement Learning is about learning from mistakes - although all machine learning algorithms depend on making sense of the magnitude of error…
and
This is Applied Exploration, a newsletter about SOTA Machine Learning in practice.
and