Neural Architecture Search with Reinforcement Learning
Citations
9 citations
9 citations
Cites methods from "Neural Architecture Search with Rei..."
...Examples include using smaller architectures for the search and stacking them at the last step [21], [22], reducing the number of epochs [23], computing the validation performance from a randomly initialised DNN [24], estimating the accuracy performance of DNN for a large budget (time) when trained with a smaller budget [25], sharing the weights of previously trained DNN [4], imposing a time budget [26], and using information from data relatively...
[...]
9 citations
9 citations
Cites background from "Neural Architecture Search with Rei..."
...To relieve this burden, some researchers introduce neural architecture search (NAS) methods [2,56,23,46] into this field, and obtain excellent results [5, 22,52,30]....
[...]
...thousands of GPU days) and computationally expensive via reinforcement learning [56,2,57,39] or evolutionary algorithms [29,35]....
[...]
9 citations
Cites background from "Neural Architecture Search with Rei..."
...), various different approaches have been suggested in recent years with a focus on evolutionary approaches [30], [31] and reinforcement-based approaches [32]....
[...]
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)....
[...]