Semantic Scholar Open Access 2017 948 sitasi

Evolving Deep Neural Networks

R. Miikkulainen J. Liang Elliot Meyerson Aditya Rawal Daniel Fink +6 lainnya

Lihat Sumber DOI

Abstrak

Abstract The success of deep learning depends on finding an architecture to fit the task. As deep learning has scaled up to more challenging tasks, the architectures have become difficult to design by hand. This paper proposes an automated method, CoDeepNEAT, for optimizing deep learning architectures through evolution. By extending existing neuroevolution methods to topology, components, and hyperparameters, this method achieves results comparable to best human designs in standard benchmarks in object recognition and language modeling. It also supports building a real-world application of automated image captioning on a magazine website. Given the anticipated increases in available computing power, evolution of deep networks is promising approach to constructing deep learning applications in the future.

Topik & Kata Kunci

Computer Science

Penulis (11)

R. Miikkulainen

J. Liang

Elliot Meyerson

Aditya Rawal

Daniel Fink

Olivier Francon

B. Raju

H. Shahrzad

Arshak Navruzyan

Nigel P. Duffy

B. Hodjat

Format Sitasi

APA MLA BibTeX

Miikkulainen, R., Liang, J., Meyerson, E., Rawal, A., Fink, D., Francon, O. et al. (2017). Evolving Deep Neural Networks. https://doi.org/10.1016/B978-0-12-815480-9.00015-3

Akses Cepat

Lihat di Sumber doi.org/10.1016/B978-0-12-815480-9.00015-3

Informasi Jurnal

Tahun Terbit: 2017
Bahasa: en
Total Sitasi: 948×
Sumber Database: Semantic Scholar
DOI: 10.1016/B978-0-12-815480-9.00015-3
Akses: Open Access ✓