ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Creative AI Through Evolutionary Computation: Principles and Examples | JoVE Visualize

Home
Research Domains
Information And Computing Sciences

Creative AI Through Evolutionary Computation: Principles and Examples

Risto Miikkulainen¹

¹The University of Texas at Austin and Cognizant Technology Solutions, San Francisco, USA.

SN Computer Science|March 29, 2021

View abstract on PubMed

Summary

Artificial intelligence (AI) excels at discovering novel solutions in complex problem spaces, not just replicating existing knowledge. Evolutionary computation offers a powerful approach for creative AI, potentially succeeding deep learning.

Area of Science:

Artificial Intelligence
Computational Intelligence
Evolutionary Computation

Background:

Current AI primarily models known information.
Novel solutions are often found in complex, high-dimensional search spaces.

Purpose of the Study:

To highlight the potential of AI in generating novel solutions.
To position evolutionary computation as a key technique for creative AI.

Main Methods:

Utilizing population-based search techniques.
Applying variants of evolutionary computation.

Main Results:

Evolutionary computation effectively navigates large, complex search spaces.
Creative solutions to real-world problems can be generated.

Conclusions:

Creative AI powered by evolutionary computation is poised to be the next significant advancement beyond deep learning.

Keywords:

Decision making Evolutionary computation

Artificial Intelligence

Evolutionary Computation

Creative Ai Through Evolutionary Computation: Principles And Examples

Machine creativity

Real-world applications

Surrogate modeling