Search
Abstract
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.
Citations
-
0
CrossRef
-
0
Web of Science
-
0
Scopus
Cite as
Full text
full text is not available in portal
Keywords
Details
- Category:
- Monographic publication
- Type:
- rozdział, artykuł w książce - dziele zbiorowym /podręczniku w języku o zasięgu międzynarodowym
- Title of issue:
- Artificial Intelligence and Soft Computing strony 271 - 279
- Language:
- English
- Publication year:
- 2020
- Bibliographic description:
- Wrosz I.: Neural Network Subgraphs Correlation with Trained Model Accuracy// Artificial Intelligence and Soft Computing. Part 1/ : , 2020, s.271-279
- DOI:
- Digital Object Identifier (open in new tab) 10.1007/978-3-030-61401-0_26
- Sources of funding:
-
- Statutory activity/subsidy
- Verified by:
- Gdańsk University of Technology
seen 124 times
Recommended for you
Embedded Representations of Wikipedia Categories
- J. Majkutewicz,
- J. Szymański,
- A. Sobecki
- + 2 authors