joeddav/devol
A genetic algorithm framework for automated neural architecture search in Keras.
Not currently ranked — collecting fresh signals.
star history
DEvol (DeepEvolution) uses genetic algorithms to automatically search for optimal neural network architectures. Each candidate network is encoded as a fixed-width genome describing layer types, activation functions, dropout rates, batch normalization, and pooling settings. The tool evolves populations of architectures over generations, applying crossover and mutation to improve model performance on classification tasks. It targets Keras models and was demonstrated achieving 99.4% accuracy on MNIST without manual architecture design.
Frequently asked
- What is joeddav/devol?
- A genetic algorithm framework for automated neural architecture search in Keras.
- Is devol open source?
- Yes — joeddav/devol is open source, released under the MIT license.
- What language is devol written in?
- joeddav/devol is primarily written in Python.
- How popular is devol?
- joeddav/devol has 951 stars on GitHub.
- Where can I find devol?
- joeddav/devol is on GitHub at https://github.com/joeddav/devol.