C++/Python implementation of fully evolvable Artificial Neural Networks. Uses the ES-HyperNEAT algorithms to indirectly encode ANNs with bio-mimetic patterns (repetitions, symmetry...), large number of neurons and relative robustness to input/output variations between generations. The API is served in Python and computations are performed in C++.
To generate directed graphs for the genomes. Can only be fetched by system installer (apt-get, yum, ...). See https://graphviz.org/download/ for instructions
To generate non-interactive images of ANN (through plotly).
Due to inconsistent support, left as an optional dependency.
Use pip install abrain[...,kaleido] to get it
Order-independent ANN evaluation (with back buffer)?
Crossover / historical markings
MANN Integration
Misc:
Advanced usage
move to scikit/poetry/... ?
CI/CD
no loadimage plugion for "svg:cairo" for pdf outputFAQs
NeuroEvolution in Python backed by C++ computations
We found that abrain demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
Research
The Socket Research Team breaks down a malicious wrapper package that uses obfuscation to harvest credentials and exfiltrate sensitive data.
Research
Security News
Attackers used a malicious npm package typosquatting a popular ESLint plugin to steal sensitive data, execute commands, and exploit developer systems.
Security News
The Ultralytics' PyPI Package was compromised four times in one weekend through GitHub Actions cache poisoning and failure to rotate previously compromised API tokens.