Explaining Artificial Intelligence Generation and Creativity: Human interpretability for novel ideas and artifacts
Authors:
- 28 June 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Magazine
- Vol. 39 (4) , 85-95
Abstract
Creativity is often thought of as the pinnacle of human achievement, but artificial intelligence (AI) is now starting to play a central role in creative processes, whether autonomously or in collaboration with people. Widespread deployment is now pushing for explanations on how creative AI is working, whether to engender trust, enable action, provide a basis for evaluation, or for intrinsic reasons. In this article, we review various motivations, algorithms, and methods for explaining either the workings of generative/creative AI algorithms or the generative/creative artifacts they produce.Keywords
This publication has 16 references indexed in Scilit:
- Autonomous Intentionality in Computationally Creative Systems2019
- A Style-Based Generator Architecture for Generative Adversarial Networks2019
- Explaining Explanations in AI2019
- TED2019
- Unifying Human and Statistical Evaluation for Natural Language Generation2019
- A big data approach to computational creativity: The curious case of Chef WatsonIBM Journal of Research and Development, 2019
- The Intuitive Appeal of Explainable MachinesSSRN Electronic Journal, 2018
- Robust prediction of individual creative ability from brain functional connectivityProceedings of the National Academy of Sciences, 2018
- Human-level concept learning through probabilistic program inductionScience, 2015
- The Creative Mind2004