Neural Architecture Search with Reinforcement Learning
Citations
2 citations
2 citations
2 citations
Cites methods from "Neural Architecture Search with Rei..."
...From human design to NAS (Neural Architecture Search)[9]....
[...]
...Recently, Google just published its new achievements—EfficientNets[6], which use Neural Architecture Search to design a new baseline network and scale it up to obtain a family of powerful models, result in a series of 8 models (EfficientNet-B0-B7) including the baseline, achieved a new state-of-art with 84.4% top-1 / 97.1% top-5 accuracy on ImageNet, while being 8.4x smaller and 6.1x faster than the previous best existing ConvNet....
[...]
2 citations
Cites background from "Neural Architecture Search with Rei..."
...The design of neural architectures has always been an active research topic in DNNs, aiming to discover effective connectivity patterns for building networks, in manually designed [33, 14, 43, 13, 51, 32] or automatic [52, 31, 53, 22] manners....
[...]
...In neural architecture search (NAS) [52, 53, 31, 30, 22, 45, 3, 44, 37], tremendous efforts have been devoted to discovering performant architectures in a broad yet structured architecture space....
[...]
2 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)....
[...]