Creative Generation of 3D Objects with Deep Learning and Innovation Engines
Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review
Standard
Creative Generation of 3D Objects with Deep Learning and Innovation Engines. / Lehman, Joel Anthony; Risi, Sebastian; Clune, Jeff.
Proceedings of the Seventh International Conference on Computational Creativity: ICCC 2016. Sony CSL Paris, 2016. p. 180-187.Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Creative Generation of 3D Objects with Deep Learning and Innovation Engines
AU - Lehman, Joel Anthony
AU - Risi, Sebastian
AU - Clune, Jeff
N1 - Conference code: 7
PY - 2016/6/30
Y1 - 2016/6/30
N2 - Advances in supervised learning with deep neural networks have enabled robust classification in many real world domains. An interesting question is if such advances can also be leveraged effectively for computational creativity. One insight is that because evolutionary algorithms are free from strict requirements of mathematical smoothness, they can exploit powerful deep learning representations through arbitrary computational pipelines. In this way, deep networks trained on typical supervised tasks can be used as an ingredient in an evolutionary algorithm driven towards creativity. To highlight such potential, this paper creates novel 3D objects by leveraging feedback from a deep network trained only to recognize 2D images. This idea is testedby extending previous work with Innovation Engines, i.e. a principled combination of deep learning and evolutionary algorithms for computational creativity. The results of this automated process are interesting and recognizable 3D-printable objects, demonstrating the creative potential for combining evolutionary computation and deep learning in this way.
AB - Advances in supervised learning with deep neural networks have enabled robust classification in many real world domains. An interesting question is if such advances can also be leveraged effectively for computational creativity. One insight is that because evolutionary algorithms are free from strict requirements of mathematical smoothness, they can exploit powerful deep learning representations through arbitrary computational pipelines. In this way, deep networks trained on typical supervised tasks can be used as an ingredient in an evolutionary algorithm driven towards creativity. To highlight such potential, this paper creates novel 3D objects by leveraging feedback from a deep network trained only to recognize 2D images. This idea is testedby extending previous work with Innovation Engines, i.e. a principled combination of deep learning and evolutionary algorithms for computational creativity. The results of this automated process are interesting and recognizable 3D-printable objects, demonstrating the creative potential for combining evolutionary computation and deep learning in this way.
M3 - Article in proceedings
SN - 9782746691551
SP - 180
EP - 187
BT - Proceedings of the Seventh International Conference on Computational Creativity
PB - Sony CSL Paris
T2 - International Conference on Computational Creativity
Y2 - 27 June 2016 through 1 July 2016
ER -
ID: 81058618