Archive - Applied Exploration

New

Say Goodbye to Aggregate Metrics: Track Your Time-Series Predictions over Time

Get Insights into Your Forecasting Model with Krisi and Be Aware of Regime Changes

May 5 •

Daniel Szemerey

and

Mark Aron Szulyovszky

April 2023

What is Adaptive Time Series ML and why is it so much faster?

Why we ended up building a Time Series Adaptive ML Engine from scratch. Adaptive Backtesting and Composite Models with speed!

Apr 19 •

Daniel Szemerey

and

Mark Aron Szulyovszky

October 2022

Zen and the Art of Generalisation

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…

Oct 6, 2022 •

Daniel Szemerey

and

Mark Aron Szulyovszky

June 2022

The dark side of Graph Neural Networks

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…

Jun 27, 2022 •

Daniel Szemerey

and

Mark Aron Szulyovszky

How I Learned to Stop Worrying and Love Graphs

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…

Jun 13, 2022 •

Daniel Szemerey

and

Mark Aron Szulyovszky

#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