This is the code base used to reproduce the experiments in the paper:

Nguyen A, Yosinski J, Clune J. "Innovation Engines: Automated creativity and improved stochastic optimization via Deep Learning". Proceedings of the Genetic and Evolutionary Computation Conference (GECCO '15), 2015.

If you use this software in an academic article, please cite:

@inproceedings{nguyen2015innovation,
  title={Innovation Engines: Automated Creativity and Improved Stochastic Optimization via Deep Learning},
  author={Nguyen, Anh and Yosinski, Jason and Clune, Jeff},
  booktitle={Genetic and Evolutionary Computation Conference (GECCO), 2015 IEEE Conference on},
  year={2015}
}

For more information regarding the paper, please visit www.evolvingai.org/InnovationEngine

This code base is a fork from the [initial project] (https://github.com/Evolving-AI-Lab/fooling).

• It has support for the latest Caffe.
• Experiments are in here
  • Novelty Search
  • MAP-Elites
    • CPPN without Sine waves experiment shows to create a lot of recognizable images.
  • Single-class EA

To start off, please refer to the documentation in the initial [project] (https://github.com/Evolving-AI-Lab/fooling)

Feel free to create github issues. We will help you as we can.

MIT License.