Neural Architecture Search with Reinforcement Learning
Citations
239 citations
Cites background from "Neural Architecture Search with Rei..."
...In the literature, an effective way to generate rich representations is using powerful hand-designed network architectures, such as residual networks (ResNets) [12] as well as their diverse variants [40, 43, 34, 7] or designing networks based on AutoML techniques [47, 26]....
[...]
234 citations
Cites methods from "Neural Architecture Search with Rei..."
...– NASNets NASNets [23] are a family of networks automatically generated by reinforcement learning using a policy gradient algorithm to optimize architectures [28]....
[...]
233 citations
Cites background from "Neural Architecture Search with Rei..."
...Neural architecture search [51] takes this a step further and trains an agent with the goal of designing entire network architectures, using accuracy as the progress (reward) signal....
[...]
214 citations
213 citations
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)....
[...]