Document Type

Article

Publication Date

8-20-2024

Publication Title

Empirical Software Engineering

Volume

29

Pages

1 - 61

Publisher Name

Springer

Abstract

Many engineering organizations are reimplementing and extending deep neural networks from the research community. We describe this process as deep learning model reengineering. Deep learning model reengineering — reusing, replicating, adapting, and enhancing state-of-the-art deep learning approaches — is challenging for reasons including under-documented reference models, changing requirements, and the cost of implementation and testing.

Comments

Author Posting © The Author(s), 2024. This article is posted here by permission of Springer for personal use and redistribution. This article was published open access in Empirical Software Engineering, VOL.29, (August 20, 2024),https://doi.org/10.1007/s10664-024-10521-0.

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Share

COinS