A Survey on Evolutionary Neural Architecture Search
By Yuqiao Liu, Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen. IEEE Transactions on Neural Networks and Learning Systems, 2020
590 citations recorded by the source corpus.
Deep neural networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is usually manually designed with rich expertise. However, such a design process is labor-intensive because of the trial-and-error process and also not easy to realize due to the rare expertise in practice. Neural architecture search (NAS) is a type of technology that can design the architectures automatically. Among different methods to realize NAS, the evolutionary computation (EC) methods have recently gained much attention and success. Unfortunately, there has not yet been a comprehensive summary of the EC-based NAS algorithms. This article reviews over 200 articles of most recent EC-based NAS methods in light of the core components, to systematically discuss their design principles and justifications on the design. Furthermore, current challenges and issues are also discussed to identify future research in this emerging field.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/50544ed8e618368d025a4ed32d604cfc21932c59
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Swarat Chaudhuri
- Rishabh Singh
- Ali Asghar Heidari
- Huiling Chen
- Armando Solar-Lezama
- Oleksandr Polozov
- Kevin Ellis
- Iman Ahmadianfar
Citations in the corpus
- Structured Pruning for Deep Convolutional Neural Networks: A Survey (2023, methodology): “Simple taxonomy involves Bayesian optimization [301], evolutionary methods [39], gradient-based methods [302], and reinforcement learning [303].”
- INFO: An efficient optimization algorithm based on weighted mean of vectors (2022, background): “Therefore, network architecture search (NAS) based on evolutionary algorithms has become a hot topic [10].”
- Neurosymbolic Programming (2021, background): “Evolutionary methods are also a popular choice for architecture search for neural networks (Liu et al., 2021).”