Neural Architecture Search with Reinforcement Learning
Citations
10 citations
10 citations
10 citations
Cites methods from "Neural Architecture Search with Rei..."
...Based on the discrete space of different layers in architectures, RL methods [6, 9] use policy optimization to choose a layer’s type and corresponding hyperparameters....
[...]
10 citations
Cites background from "Neural Architecture Search with Rei..."
...Automating these design decisions, commonly referred to as hyperparameter search [14] or AutoML [99], to reduce human effort is an active area of current research, and many algorithms have been proposed, including simple grid search [49], random search [14], reinforcement learning [12, 115], evolutionary computation [97], and gradient decent [60]....
[...]
10 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)....
[...]