Neural Architecture Search with Reinforcement Learning
Citations
45 citations
Cites methods from "Neural Architecture Search with Rei..."
...The PG approach adopted in this paper for program synthesis is closely related to neural architecture search (Zoph & Le, 2017) and neural combinatorial optimization (Bello et al., 2016), where variants of PG are used to train an RNN and a pointer network (Vinyals et al., 2015) to perform…...
[...]
45 citations
Cites methods from "Neural Architecture Search with Rei..."
...Following the settings in NAS works [27, 50], we regard Conv-BN-Relu as a complete block, thus the gates are always placed after Relu activation functions....
[...]
45 citations
Cites background from "Neural Architecture Search with Rei..."
...Additionally, an innovative neural network called Neural Architecture Search (NASNet) [57, 58, 40] examines a database of dimension convolution layers to automate an effective architecture design, surpassing prior humandefined neural networks....
[...]
44 citations
44 citations
Cites background from "Neural Architecture Search with Rei..."
...Architecture search has also been recently formulated as a reinforcement learning problem with impressive results [25]....
[...]
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)....
[...]