Neural Architecture Search with Reinforcement Learning
Citations
165 citations
162 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...Compared to RL-based [31, 30, 20] and gradient-based NAS methods [16, 26, 3], the evolutionary search can stably meet hard constraints, e....
[...]
...It can perform with a pre-trained backbone network and search with the previous NAS algorithm [30]....
[...]
...Compared to RL-based [32, 31, 21] and gradient-based NAS methods [17, 27, 3], the evolutionary search can stably meet hard constraints, e.g., FLOPs or inference speed....
[...]
...NAS [30] and NASNet [31] use reinforcement learning (RL) to determine neural architectures sequentially....
[...]
...On image classification [30, 31, 22], searched networks reach or even surpass the performance of the hand-crafted networks....
[...]
160 citations
158 citations
Cites background from "Neural Architecture Search with Rei..."
...Applications of RL on NLP range widely, from Question Answering (QA) [140], Dialogue systems [141], Machine Translation [142], to an integration of NLP and Computer Vision tasks, such as Visual Question Answering (VQA) [143], Image Caption [144], etc....
[...]
157 citations
Cites methods from "Neural Architecture Search with Rei..."
...Recently, automatic model search [18,21,22,32,38,39] has become a promising trend for CNN architecture design....
[...]
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)....
[...]