Explaining Artificial Intelligence Generation and Creativity Human interpretability for novel ideas and artifacts

被引:13
作者
Das, Payel [1 ]
Varshney, Lav R. [2 ,3 ]
机构
[1] IBM Thomas J Watson Res Ctr, IBM Res AI, Ossining, NY 10562 USA
[2] Univ Illinois, Elect & Comp Engn, Champaign, IL USA
[3] Kocree Inc, Champaign, IL USA
关键词
Software engineering;
D O I
10.1109/MSP.2022.3141365
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
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. © 1991-2012 IEEE.
引用
收藏
页码:85 / 95
页数:11
相关论文
共 44 条
  • [1] Agarwal S., 2019, PROC ICML WORKSHOP D
  • [2] [Anonymous], 1985, INT COMMUN HEAT MASS, DOI DOI 10.1016/0735-1933(85)90003-X
  • [3] Robust prediction of individual creative ability from brain functional connectivity
    Beaty, Roger E.
    Kenett, Yoed N.
    Christensen, Alexander P.
    Rosenberg, Monica D.
    Benedek, Mathias
    Chen, Qunlin
    Fink, Andreas
    Qiu, Jiang
    Kwapil, Thomas R.
    Kane, Michael J.
    Silvia, Paul J.
    [J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2018, 115 (05) : 1087 - 1092
  • [4] Bender E. M., 2020, P 58 ANN M ASS COMPU, P5185
  • [5] Boden M.A., 2004, CREATIVE MIND MYTHS
  • [6] Bommasani R., 2021, ARXIV210807258 CSLG
  • [7] Chenthamarakshan V, 2020, Advances in Neural Information Processing Systems, V33, P4320
  • [8] Cintas C., 2021, PROC SYNTHETIC DATA
  • [9] Clouatre L., 2019, ARXIV190102199 CSLG
  • [10] Collingwood R.G., 1938, PRINCIPLES ART