Neural Architecture Search with Reinforcement Learning
Citations
50 citations
Cites methods from "Neural Architecture Search with Rei..."
...NASNet model is inspired by the automated neural architecture search (NAS) method introduced by Zoph et al [70]....
[...]
...NASNet architecture was designed by Zoph et al. [71]....
[...]
49 citations
Cites methods from "Neural Architecture Search with Rei..."
...Tan et al. (Tan et al., 2019) are one of the first to use NAS for efficient CNN by adding latency into the optimization constraint and use reinforcement learning (Zoph & Le, 2016; Zoph et al., 2018) to maximize the reward (high accuracy and low latency)....
[...]
49 citations
Cites methods from "Neural Architecture Search with Rei..."
...They used NAS (Neural Architecture Search) framework from [14] as the main search method for their NASNets....
[...]
49 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...An empirical approximation of the above quantity is to sample the outputs of the controller [48]:...
[...]
...In order to reduce variance of this estimation, we employ a baseline function b [48]:...
[...]
...Our gated controller for visual and acoustic modality is inspired by the controller used by Zoph and Le [48], where they use a Recurrent Neural Network (RNN) controller to determine the structure of a CNN....
[...]
49 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)....
[...]