Archive - Applied Exploration

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…

Daniel Szemerey

and

Mark Aron Szulyovszky

Oct 6, 2022

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…

Daniel Szemerey

and

Mark Aron Szulyovszky

Jun 27, 2022

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…

Daniel Szemerey

and

Mark Aron Szulyovszky

Jun 13, 2022

May 2021

Deep Reinforcement Learning is about learning from mistakes - although all machine learning algorithms depend on making sense of the magnitude of error…

Daniel Szemerey

and

Mark Aron Szulyovszky

May 4, 2021

This is Applied Exploration, a newsletter about SOTA Machine Learning in practice.

Daniel Szemerey

and

Mark Aron Szulyovszky

May 1, 2021

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts