Neural Architecture Search with Reinforcement Learning
Citations
106 citations
Cites background from "Neural Architecture Search with Rei..."
...Google's AutoML project seems to provide some promise in using reinforcement learning and evolutionary algorithms to design neural networks, but timely implementation of these approaches would require significant compute power unavailable to a typical researcher.(27,28) Nonetheless, various rules of thumb have been developed in the larger deep learning community....
[...]
103 citations
103 citations
102 citations
Cites methods from "Neural Architecture Search with Rei..."
...[43] However, such methods typically require on the order of ̃10,000 trials, which is much more than the ̃500 trials used in our work....
[...]
102 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...Many recent work has been dedicated to designing effective networks for sequence processing (Greff et al., 2015; Balduzzi and Ghifary, 2016; Miao et al., 2016; Zoph and Le, 2016; Lee et al., 2017)....
[...]
...4https://github.com/hitvoice/DrQA Setup Our training configuration largely follows prior work (Zaremba et al., 2014; Gal and Ghahramani, 2016; Zoph and Le, 2016)....
[...]
...Setup Our training configuration largely follows prior work (Zaremba et al., 2014; Gal and Ghahramani, 2016; Zoph and Le, 2016)....
[...]
References
123,388 citations
111,197 citations
55,235 citations
"Neural Architecture Search with Rei..." refers methods in this paper
...Along with this success is a paradigm shift from feature designing to architecture designing, i.e., from SIFT (Lowe, 1999), and HOG (Dalal & Triggs, 2005), to AlexNet (Krizhevsky et al., 2012), VGGNet (Simonyan & Zisserman, 2014), GoogleNet (Szegedy et al., 2015), and ResNet (He et al., 2016a)....
[...]
42,067 citations
31,952 citations
"Neural Architecture Search with Rei..." refers methods in this paper
...Along with this success is a paradigm shift from feature designing to architecture designing, i.e., from SIFT (Lowe, 1999), and HOG (Dalal & Triggs, 2005), to AlexNet (Krizhevsky et al., 2012), VGGNet (Simonyan & Zisserman, 2014), GoogleNet (Szegedy et al., 2015), and ResNet (He et al., 2016a)....
[...]