Neural Architecture Search with Reinforcement Learning
Citations
24 citations
24 citations
24 citations
Cites background from "Neural Architecture Search with Rei..."
...Subsequent works have made various improvements, including the usage of dilated convolutions [4, 5, 6, 56, 57], encoder-decoder architecture [2, 22, 8], Conditional Random Fields (CRF) for post-processing [60, 4, 5], spatial pyramid pooling to capture multi-scale features [59, 5, 6] and Neural Architecture Search (NAS) [65] to search for the best-performing architectures [3, 24]....
[...]
24 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...studies [17], [20], [43], [49] at the cost of exploration time....
[...]
...ENAS successfully achieved a speedup of more than 4,000× and 3-8× relative to NAS [17] and Darts [19], respectively, with only negligible accuracy loss....
[...]
...Therefore, several neural architecture search (NAS) techniques have been proposed to efficiently explore this enormous design space based on various search algorithms, such as reinforcement learning (RL) [17], [18], gradient descent [19], and Bayesian optimization [20]....
[...]
...1(b) illustrates the main differences in design goals between conventional NAS techniques [17]–[20] and our APNAS framework....
[...]
...Among various automation techniques, NAS [17] was the first work, where an RNN was used to generate DNN models and was trained...
[...]
24 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)....
[...]