Neural Architecture Search with Reinforcement Learning
Citations
46 citations
46 citations
Cites methods from "Neural Architecture Search with Rei..."
...Hence, to prevent such premature convergence and reasoningshortcut overfitting, we adopt the 2-phase training strategy that is widely used in Neural Architecture Search (Zoph and Le, 2016; Pham et al., 2018)....
[...]
...Moreover, Modular Networks’ architectures are predicted dynamically on each data point, while previous NAS methods learn a single cell structure independent of the example....
[...]
...However, Neural Architecture Search aims to learn the structure of the individual CNN/RNN cell with fixed inter-connections between the cells, while Modular Networks have preset individual modules but learns the way to assemble them into a larger network....
[...]
...Architecture Learning Our work also shares the spirit of recent research on Neural Architecture Search (NAS) (Zoph and Le, 2016; Pham et al., 2018; Liu et al., 2018), since the architecture of the model is learned dynamically based on controllers instead of being manually-designed....
[...]
46 citations
46 citations
46 citations
Cites background from "Neural Architecture Search with Rei..."
...To serve applications under all these scenarios with drastically different requirements, different models tailored for different resource budgets can be devised either manually [14, 15, 16, 37] or automatically through neural architecture search [39, 56, 57]....
[...]
...Neural Architecture Search Neural architecture search (NAS) gains increasing popularity in recent study [4, 21, 24, 27, 34, 43, 45, 56]....
[...]
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)....
[...]