Neural Architecture Search (NAS) is a computationally demanding process of finding optimal neural network architecture for a given task. Conceptually, NAS comprises applying a search strategy on a predefined search space accompanied by a performance evaluation method. The design of search space alone is expected to substantially impact NAS efficiency. We consider neural networks as graphs and find a correlation between the presence of subgraphs and the network’s final test accuracy by analyzing a dataset of convolutional neural networks trained for image recognition. We also consider a subgraph based network distance measure and suggest opportunities for improved NAS algorithms that could benefit from our observations.
Authors
Additional information
- DOI
- Digital Object Identifier link open in new tab 10.1007/978-3-030-61401-0_26
- Category
- Publikacja monograficzna
- Type
- rozdział, artykuł w książce - dziele zbiorowym /podręczniku w języku o zasięgu międzynarodowym
- Language
- angielski
- Publication year
- 2020
