Neural Architecture Search with Reinforcement Learning
Citations
30 citations
Cites methods from "Neural Architecture Search with Rei..."
...In future works, we aim to introduce the AutoML [27, 52] into the FM to automatically select and determine the final basic component and fractal depth....
[...]
29 citations
Cites background from "Neural Architecture Search with Rei..."
...Furthermore, even with this renewed interest from many deep learning researchers and practitioners it still seems that most of the existing NAS research predominantly focuses on using Evolutionary Algorithms [19,21,15], Bayesian Optimisation [4,10], and Reinforcement Learning [24,1,25]....
[...]
29 citations
29 citations
29 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...Along this direction, a number of network search methods have been developed, including evolution [26, 31], surrogate model based search [18, 21], and reinforcement learning [36, 37, 34, 4]....
[...]
...Reinforcement learning (RL) methods [4, 36, 34, 37, 24] formulate the generation of a neural architecture as an agent’s action, whose space is identical to the architecture search space....
[...]
...For example, [36] used a recurrent neural network (RNN) to sample a sequence of string which encoded the neural architecture....
[...]
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)....
[...]