Neural Architecture Search with Reinforcement Learning
Citations
9 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...Last but not least, even with the same training data set but given different compression techniques or optimization parameters, hundreds of or even more different DNN models can be generated using neural architecture search techniques [9], [10], among which no single model is a clear winner in terms of all important metrics such as accuracy, latency and energy....
[...]
...As a consequence, even with the same training data set but given different compression techniques or optimization parameters, hundreds of or even more different DNN models can be generated using neural architecture search techniques [9], [10]....
[...]
...On the other hands, Oracle represents a “one for one” approach (similar to those proposed by recent studies [4], [5], [9], [10], [13], [15]–[17]) and chooses the best DNN model for each individual edge device to maximize the expected QoE, under the assumption that the parameter θ in the QoE model is perfectly known a priori....
[...]
...2) Poor scalability: Many research studies have leveraged AutoML and neural architecture search techniques to identify the optimal DNN model for a specific target edge device [4], [5], [9], [10], [13], [15]–[17]....
[...]
...Given a large set of DNN models pre-trained in the cloud using state-of-the-art AutoML and neural architecture search techniques [9], [10], [13], [15], our DNN model selection engine constructs a QoE model based on users’ QoE feedback and selects appropriate DNN models for edge devices, balancing exploration and exploitation....
[...]
9 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...The original method in [8] uses the controller to generate the entire network at once....
[...]
...A major limitation of these approaches [8], [9] is the steep computational requirement for the search process itself, often requiring weeks of wall clock time on hundreds of GPU cards....
[...]
...The second and third groups range from earlier methods [8], [16], [17] that are oriented towards “proof-of-concept" for NAS, to more recent methods [9], [10], [15], [19], many of which improve state-of-the-art results on...
[...]
...Zoph and Le [8] first apply this method in architecture search to train a recurrent neural network controller that constructs networks....
[...]
9 citations
Additional excerpts
...This rapid popularization of different types of neural networks brought into the neuroevolution field challenges to try new techniques by combining and expanding these varied components into appropriate topologies and configurations to solve problems even more effectively and is also referred to as the neural architecture search problem [12]....
[...]
9 citations
Cites background from "Neural Architecture Search with Rei..."
..., 2012); the network architecture search (NAS) methods based on reinforcement learning (Zoph and Le, 2016; Zoph et al., 2018; Liu et al., 2018)....
[...]
..., 2012) or network architecture search methods (Zoph and Le, 2016) for searching....
[...]
9 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)....
[...]