Neural Architecture Search with Reinforcement Learning
Citations
1,592 citations
1,342 citations
Cites background or methods or result from "Neural Architecture Search with Rei..."
...Overview of Neural Architecture Search [44]....
[...]
...Our approach makes use of the recently proposed Neural Architecture Search (NAS) framework [44], which uses a policy gradient algorithm to optimize architecture configurations....
[...]
...We note that this search procedure is almost 7× faster than previous approaches [44]...
[...]
...2In particular, we note that previous architecture search [44] employed 800 GPUs for 28 days resulting in 22,400 GPU-hours....
[...]
...However, if the search space is properly constructed, architectural elements can transfer across datasets [44]....
[...]
1,278 citations
Cites methods from "Neural Architecture Search with Rei..."
...Our approach is inspired by recent advances in architecture search, where reinforcement learning and evolution have been used to discover model architectures from data [71, 4, 72, 7, 35, 13, 34, 46, 49, 63, 48, 9]....
[...]
...Search algorithm details: The search algorithm that we used in our experiment uses Reinforcement Learning, inspired by [19, 23, 33, 52]....
[...]
...Search algorithm details: The search algorithm that we used in our experiment uses Reinforcement Learning, inspired by [71, 4, 72, 5]....
[...]
...In our experiments, we use Reinforcement Learning [23] as the search algorithm, but we believe the results can be further improved if better algorithms are used [21, 24]....
[...]
...In our experiments, we use Reinforcement Learning [71] as the search algorithm, but we believe the results can be further improved if better algorithms are used [48, 39]....
[...]
1,263 citations
1,201 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...Previous works [30, 31, 20] has demonstrated the effectiveness of such methods in finding accurate and efficient ConvNet models....
[...]
...For example, [30, 31] trains the architecture on the CIFAR10 dataset, and [20] trains on ImageNet but only for 5 epochs....
[...]
...Previous works [30, 31, 16, 11, 12] focus on cell level architecture search....
[...]
...Many previous works [30, 31, 20] use reinforcement learning (RL) to guide the search and a typical flow is illustrated in Figure 2(b)....
[...]
...Starting from [30], recent works adopt neural architecture search (NAS) to explore the design space automatically....
[...]
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)....
[...]