Creative AI Through Evolutionary Computation: Principles and Examples
This work addresses the challenge of generating innovative solutions in AI, which could impact various real-world applications, though it is more conceptual and incremental in nature.
The paper argues that evolutionary computation is well-suited for creative AI by exploring large search spaces to find novel solutions, positioning it as a potential successor to deep learning.
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 learning."