Semantic Scholar Open Access 2017 2123 sitasi

Progressive Neural Architecture Search

Chenxi Liu Barret Zoph Jonathon Shlens Wei Hua Li-Jia Li +4 lainnya

Abstrak

We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms. Our approach uses a sequential model-based optimization (SMBO) strategy, in which we search for structures in order of increasing complexity, while simultaneously learning a surrogate model to guide the search through structure space. Direct comparison under the same search space shows that our method is up to 5 times more efficient than the RL method of Zoph et al. (2018) in terms of number of models evaluated, and 8 times faster in terms of total compute. The structures we discover in this way achieve state of the art classification accuracies on CIFAR-10 and ImageNet.

Topik & Kata Kunci

Computer Science Mathematics

Penulis (9)

Chenxi Liu

Barret Zoph

Jonathon Shlens

Wei Hua

Li-Jia Li

Li Fei-Fei

A. Yuille

Jonathan Huang

K. Murphy

Format Sitasi

APA MLA BibTeX

Liu, C., Zoph, B., Shlens, J., Hua, W., Li, L., Fei-Fei, L. et al. (2017). Progressive Neural Architecture Search. https://doi.org/10.1007/978-3-030-01246-5_2

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →

Lihat di Sumber doi.org/10.1007/978-3-030-01246-5_2

Informasi Jurnal

Tahun Terbit: 2017
Bahasa: en
Total Sitasi: 2123×
Sumber Database: Semantic Scholar
DOI: 10.1007/978-3-030-01246-5_2
Akses: Open Access ✓