Neural Architecture Search with Reinforcement Learning
Citations
132 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...There are many related methods for neural architecture search, for example based on reinforcement learning (Zoph and Le, 2017; Zoph et al., 2017) and evolutionary algorithms (Real et al....
[...]
...(2018) showed that a well-tuned LSTM (Hochreiter and Schmidhuber, 1997) with the right training pipeline was able to outperform a recurrent cell found by neural architecture search (Zoph and Le, 2017) on the Penn Treebank dataset....
[...]
...On some benchmarks, these NAS methods have indeed led to new state-of-the-art performance (Zoph and Le, 2017; Real et al., 2018), although only at extreme computational costs on the order of 800 GPUs for two weeks....
[...]
...There are many related methods for neural architecture search, for example based on reinforcement learning (Zoph and Le, 2017; Zoph et al., 2017) and evolutionary algorithms (Real et al., 2017; Liu et al., 2017; Real et al., 2018)....
[...]
...Many prominent NAS methods (Zoph and Le, 2017; Real et al., 2017; Zoph et al., 2017; Real et al., 2018) follow a two step process, which we argue is inefficient....
[...]
131 citations
131 citations
130 citations
Cites methods from "Neural Architecture Search with Rei..."
...This work is deeply related to RL methods for neural architecture search (Zoph and Le, 2016) and their one shot (Brock et al., 2017), multi-task learning (Pasunuru and Bansal, 2019), and continual learning (Xu and Zhu, 2018; Pasunuru and Bansal, 2019) variants....
[...]
...This work is deeply related to RL methods for neural architecture search (Zoph and Le, 2016) and their one shot (Brock et al....
[...]
129 citations
Cites background from "Neural Architecture Search with Rei..."
...2017b)(Hu, Shen, and Sun 2018), and even proposed to automatically explore network architectures (Xie and Yuille 2017)(Zoph and Le 2017)....
[...]
...…better recognition performance, researchers designed deeper and deeper networks (Simonyan and Zisserman 2015)(Szegedy et al. 2015)(He et al. 2016)(Huang et al. 2017b)(Hu, Shen, and Sun 2018), and even proposed to automatically explore network architectures (Xie and Yuille 2017)(Zoph and Le 2017)....
[...]
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)....
[...]