Each challenge defines a dataset, metric, and baseline that miners compete to beat. When a model surpasses the baseline on hidden tests, validators confirm the result and trigger a payout. It's how research becomes measurable progress: open, reproducible and rewarded only on proof.
AutoML Zero serves as the network's first and flagship challenge - an open benchmark where miners evolve algorithms from scratch to prove measurable progress in AI.
What is AutoML Zero?
AutoML Zero is a revolutionary approach to machine learning that discovers algorithms from scratch, rather than just tuning existing ones. Think of it as "AI that creates AI."
The Traditional Approach
Manual Algorithm Selection
Researchers manually choose algorithms (SVM, Random Forest, Neural Networks)
Hyperparameter Tuning
Optimize existing parameters within predefined algorithm structures
Incremental Improvements
Small gains through better tuning and feature engineering
AutoML Zero Approach
Algorithm Discovery
Evolutionary algorithms discover entirely new ML algorithms from basic operations
From Scratch
Starting with only basic mathematical operations (+, -, *, /, exp, log)
Novel Discoveries
Potentially discovering algorithms humans haven't thought of yet
Start Mining
Set-up mining in less than 60 seconds. One-click CPU/GPU
Join the Beta
Limited Slots
MacOS
Windows
Linux
System Requirements
