Neural Architecture Search with Reinforcement Learning
Citations
1 citations
1 citations
Additional excerpts
...The first research along this line was a very straightforward search utilizing reinforcement learning: Construct an architecture, train it until convergence, evaluate its performance and use that (accuracy) score as a reward, then repeat [Zoph and Le, 2017, Baker et al., 2017]....
[...]
1 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...Some works use policy gradient algorithm to design networks [4], [9], [10]....
[...]
...Different from NAS [4], we use Gaussian policy to predict the number of channels....
[...]
...Besides, our method is faster than NAS [4], MetaQNN [5] and EAS [10]....
[...]
...Compared with softmax policy (as shown in (9)) used in [4], [5], [9], Gaussian policy has several advantages....
[...]
...For policy gradient methods in [4], [9], [10], the number of channels is fixed to several pre-defined numbers and is predicted through discrete softmax policy....
[...]
1 citations
1 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)....
[...]