Neural Architecture Search with Reinforcement Learning
Citations
69 citations
Cites background from "Neural Architecture Search with Rei..."
...While these architectures are designed by humans, another recent trend is the automatic search of neural architectures (neural architecture search) [240]....
[...]
69 citations
Cites methods from "Neural Architecture Search with Rei..."
...Early works of NAS adopt heuristic methods such as reinforcement learning [48] and evolutionary algorithm [41]....
[...]
...The NAS technique has applied to many computer vision tasks such as image classification [2, 24, 25, 30, 48], dense image prediction [23, 47, 3] and object detection [8, 29]....
[...]
69 citations
69 citations
68 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...These approaches have often reached or exceeded the level of accuracy obtained by architectures that were tuned manually (Zoph et al., 2017; Cai et al., 2018b; Liu et al., 2017a; Zhong et al., 2018; Zoph and Le, 2016)....
[...]
..., convolution or pooling operations) that can then be stacked to compose global networks (Zoph and Le, 2016; Liu et al., 2017a)....
[...]
...Multiple search methods have been considered to traverse the space of architectures, including reinforcement learning (RL; Zoph and Le (2016); Baker et al. (2016)), genetic algorithms (Liu et al., 2017b; Xie and Yuille, 2017; Zoph et al., 2017), and progressive search methods (Liu et al., 2017a;…...
[...]
...Finally, following previous work (Zoph and Le, 2016; Liu et al., 2018), we also consider two different types of cells: normal cells and reduction cells....
[...]
...For image classification tasks, most works define a search space in terms of cells, computational graphs of neural primitives (e.g., convolution or pooling operations) that can then be stacked to compose global networks (Zoph and Le, 2016; Liu et al., 2017a)....
[...]
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)....
[...]