Neural Architecture Search with Reinforcement Learning
Citations
6 citations
6 citations
6 citations
6 citations
Cites background from "Neural Architecture Search with Rei..."
...As designing architectures often demands detailed domain expertise and creating new datasets is expensive, there has been a substantial effort in automating the process of designing better task-specific architectures [10,54,65] and employing self-supervised methods of learning to reduce the dependence on humanannotated data [12,7,14]....
[...]
...[10,54,65], could yield better results but are computationally expensive....
[...]
6 citations
Cites background from "Neural Architecture Search with Rei..."
...Besides, NAS [9], [10] is proposed to search for network architectures with better performance....
[...]
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)....
[...]