Applied Exploration

Home
Our GitHub
Our Website
Archive
About
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 formats and algorithms, such as Computer Vision (CV) or Natural Language Processing (NLP)?
Daniel Szemerey
and
Mark Aron Szulyovszky
New
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
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
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
This is Applied Exploration, a newsletter about SOTA Machine Learning in practice.
Daniel Szemerey
and
Mark Aron Szulyovszky
Open-Core Libraries
FoldA Time Series Cross-Validation library that lets you build, deploy and update composite models easily.
KrisiLightweight Evaluation of Time Series Forecasting (Classification and Regression) with powerful Reporting.
Fold-ModelsModels and wrappers for 3rd party models to be used with `fold` (github.com/dream-faster/fold)
Links
Our Website
Our GitHub Page

Applied Exploration

AboutArchiveSitemap
© 2023 Daniel Szemerey, Mark Aron Szulyovszky
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing