Modeling Neural Architecture Search Methods for Deep Networks
This work provides a foundational tool for researchers in machine learning to systematically analyze and compare NAS techniques, though it is incremental as it builds on existing methods without introducing new algorithms.
The authors tackled the lack of a unifying model for comparing neural architecture search (NAS) methods by proposing a general abstraction framework, enabling categorization and identification of critical design areas in deep neural networks.
There are many research works on the designing of architectures for the deep neural networks (DNN), which are named neural architecture search (NAS) methods. Although there are many automatic and manual techniques for NAS problems, there is no unifying model in which these NAS methods can be explored and compared. In this paper, we propose a general abstraction model for NAS methods. By using the proposed framework, it is possible to compare different design approaches for categorizing and identifying critical areas of interest in designing DNN architectures. Also, under this framework, different methods in the NAS area are summarized; hence a better view of their advantages and disadvantages is possible.