Competing in a data science contest without reading the data
Machine learning competitions have become an extremely popular format forsolving prediction and classification problems of all sorts. The most famousexample ...
Machine learning competitions have become an extremely popular format for solving prediction and classification problems of all sorts. The most famous example is perhaps the Netflix prize. An even better example is Kaggle , an awesome startup that’s organized more than a hundred competitions over the past few years. The central component of any competition is the public leaderboard. Competitors can repeatedly submit a list of predictions and see how their predictions perform on a set of holdout labels not available to them. The leaderboard ranks all teams according to their prediction accuracy
saved by
related reading
- Preface - The Emerging Science of Machine Learning Benchmarksmlbenchmarks.org
- MAI-Thinking-1: Building a Hill-Climbing Machinemicrosoft.ai
- Thinking about High-Quality Human Data | Lil'Loglilianweng.github.io
- The ML drug discovery startup trying really, really hard to not cheat (Leash Bio)owlposting.com
- https://arxiv.org/pdf/1811.12808arxiv.org
- Good QC for RL Dataseancai.com
- A Course in Machine Learningciml.info
- MAI-Thinking-1: Building a Hill-Climbing Machinemicrosoft.ai
- Why are Machine Learning Projects so Hard to Manage? | by Lukas Biewald | Mediummedium.com
- [2203.07814] Competition-Level Code Generation with AlphaCodearxiv.org
- DataRater: Meta-Learned Dataset Curationarxiv.org
- Are AI benchmarks doomed? - by Anson Ho and Greg Burnhamepochai.substack.com