An Approach for Efficient Neural Architecture Search Space Definition
This work addresses the need for efficient and accessible neural architecture search in AutoML, particularly for users lacking advanced expertise, though it appears incremental in improving search space design.
The paper tackles the problem of time-consuming and expertise-dependent neural architecture search by proposing a novel cell-based hierarchical search space that is easy to comprehend and manipulate, aiming to optimize search-time and handle most state-of-the-art CNN architectures.
As we advance in the fast-growing era of Machine Learning, various new and more complex neural architectures are arising to tackle problem more efficiently. On the one hand their efficient usage requires advanced knowledge and expertise, which is most of the time difficult to find on the labor market. On the other hand, searching for an optimized neural architecture is a time-consuming task when it is performed manually using a trial and error approach. Hence, a method and a tool support is needed to assist users of neural architectures, leading to an eagerness in the field of Automatic Machine Learning (AutoML). When it comes to Deep Learning, an important part of AutoML is the Neural Architecture Search (NAS). In this paper, we propose a novel cell-based hierarchical search space, easy to comprehend and manipulate. The objectives of the proposed approach are to optimize the search-time and to be general enough to handle most of state of the art Convolutional Neural Networks (CNN) architectures.