Neural Architecture Search with Reinforcement Learning
Citations
71 citations
71 citations
Cites background from "Neural Architecture Search with Rei..."
...Many NAS approaches, such as deep reinforcement learning (Zoph & Le, 2016; Baker et al., 2016; Zhong et al., 2017; Pham et al., 2018) and evolutionary algorithms (Real et al., 2017; Desell, 2017; Liu et al., 2017; Suganuma et al., 2017; Xie & Yuille, 2017; Real et al., 2018), require a large n to…...
[...]
71 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...The closest existing solutions, which allow such end-toend training are probably the recent Learning to Learn approaches to nd neural net (NN) architectures [3, 45]....
[...]
...Neural networks are hard to design from scratch, and there are many proposed solution using similar Bayesian Optimization [5, 25] or Reinforcement Learning techniques [45]....
[...]
...AutoML Systems: Most automated ML systems focus on automated learning algorithm selection and hyper-parameter tuning [4, 6, 13, 23, 24, 36, 45] to make machine learning curation fully automated for non-ML experts....
[...]
70 citations
70 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...Reinforcement Learning (RL): Several RL techniques have been investigated for NAS [2, 48]....
[...]
...Zoph et al. built an RNN agent trained with Policy Gradient to design CNN and LSTM [64]....
[...]
...built an RNN agent trained with Policy Gradient to design CNN and LSTM [48]....
[...]
...MetaQNN (QL) [2] × -greedy × × Zoph (PG)[48] × RNN √ √...
[...]
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)....
[...]