Creative AI Through Evolutionary Computation: Principles and Examples

@article{Miikkulainen2021CreativeAT,
  title={Creative AI Through Evolutionary Computation: Principles and Examples},
  author={R. Miikkulainen},
  journal={Sn Computer Science},
  year={2021},
  volume={2}
}
The main power of artificial intelligence is not in modeling what we already know, but in creating solutions that are new. Such solutions exist in extremely large, high-dimensional, and complex search spaces. Population-based search techniques, i.e. variants of evolutionary computation, are well suited to finding them. These techniques make it possible to find creative solutions to practical problems in the real world, making creative AI through evolutionary computation the likely “next deep… Expand

Figures from this paper

References

SHOWING 1-10 OF 48 REFERENCES
When Novelty Is Not Enough
Deep learning in neural networks: An overview
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
Encouraging Behavioral Diversity in Evolutionary Robotics: An Empirical Study
A Hierarchical Approach to Learning the Boolean Multiplexer Function
Parallel Problem Solving from Nature PPSN VI
...
1
2
3
4
5
...