Neural Architecture Search with Reinforcement Learning
Citations
18 citations
18 citations
Cites methods from "Neural Architecture Search with Rei..."
...After that, many endeavors are conducted on reducing the high training cost of NAS....
[...]
...DARTS [23] and SNAS [44] formulate the problem of network architecture search in a differentiable manner and solve it using gradient descent....
[...]
...Tan et al. [51] introduce MNAS....
[...]
...The research of AutoML for neural architecture search can be traced back to NAS [42], which first utilizes an RNN based controller to design neural networks and proposes a reinforcement learning algorithm to optimize the framework....
[...]
...Pham et al. [22] propose ENAS, where the controller learns to search a subgraph from a large computational graph to form an optimal neural network architecture....
[...]
17 citations
Cites methods from "Neural Architecture Search with Rei..."
...The decoder is a word-based language model (Zoph and Le, 2016) which produces a sequence of nodes (e....
[...]
17 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...Neural architecture optimization is first proposed with the reinforcement learning method [30, 49], which leverages a learned policy to control the selection of operators along with the network....
[...]
...Most existing works in neural architecture search (NAS) focus on searching either stacked operators [30, 49] or repeated cell-structured directed acyclic graph [22] for the classification task....
[...]
...Aiming to discover an optimal network architecture from data, NAS has been successfully applied primarily on image classification [10, 22, 25, 30, 33, 43, 49], and lately also on object detection [8, 13], semantic segmentation [21, 26, 6], person re-identification [31], speech recognition [9], super-resolution [37], medical image analysis [48], and even generative models [14, 12] or Bayesian deep networks [2]....
[...]
17 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)....
[...]