bookmarks (hide)37
- In the last decade, industry’s demand for deep learning (DL) has increased due to its high performance in complex scenarios. Due to the DL method’s complexity, experts and non-experts rely on blackbox software packages such as Tensorflow and Pytorch. The frameworks are constantly improving, and new versions are released frequently. As a natural process in software development, the released versions contain improvements/changes in the methods and their implementation. Moreover, versions may be bug-polluted, leading to the model performance decreasing or stopping the model from working. The aforementioned changes in implementation can lead to variance in obtained results. This work investigates the effect of implementation changes in different major releases of these frameworks on the model performance. We perform our study using a variety of standard datasets. Our study shows that users should consider that changing the framework version can affect the model performance. Moreover, they should consider the possibility of a bug-polluted version before starting to debug source code that had an excellent performance before a version change. This also shows the importance of using virtual environments, such as Docker, when delivering a software product to clients.
- In enterprises, data is usually distributed across multiple data sources and stored in heterogeneous formats. The harmonization and integration of data is a prerequisite to leverage it for AI initiatives. Recently, data catalogs pose a promising solution to...
publications
(hide)68
This list of posts may not be accurate to recent changes. If you want accurate posts, but with limited sorting follow this link.
- Algorithms, 16 (9): 450 (September 2023)
- Information Sciences, (2024)
- ACM Transactions on Quantum Computing, 3 (3): 1--17 (June 2022)
- Journal of Mathematical Biology, 80 (5): 1459--1495 (Apr 1, 2020)
- Journal of Computer Languages, (2024)
- Machine Learning and Knowledge Extraction, 4 (4): 888--911 (October 2022)
- J. Artif. Int. Res., (Feb 11, 2024)
- Energy and Buildings, (2017)
- Proc. ACM Manag. Data, 1 (1): 1–25 (May 30, 2023)
- Journal of Systems and Software, (2023)
- Energy and Buildings, (2021)
- Procedia Computer Science, (2021)Proceedings of the 2nd International Conference on Industry 4.0 and Smart Manufacturing (ISM 2020).
- Frontiers in Big Data, (March 2022)
- Theoretical Computer Science, (2016)
- IEEE Transactions on Fuzzy Systems, 31 (8): 2617-2631 (August 2023)
- IEEE Access, (2023)
- Procedia Computer Science, (2023)4th International Conference on Industry 4.0 and Smart Manufacturing.
- Neurocomputing, (2022)
- 1An optimal $łess$mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" altimg="si17.svg"$\greater$$łess$mml:mrow$\greater$$łess$mml:mo stretchy="true"$\greater$($łess$/mml:mo$\greater$$łess$mml:mi$\greater$∊$łess$/mml:mi$\greater$$łess$mml:mo$\greater$,$łess$/mml:mo$\greater$$łess$mml:mi$\greater$$\updelta$$łess$/mml:mi$\greater$$łess$mml:mo stretchy="true"$\greater$)$łess$/mml:mo$\greater$$łess$/mml:mrow$\greater$$łess$/mml:math$\greater$-differentially private learning of distributed deep fuzzy modelsInformation Sciences, (February 2021)
- International Journal of Approximate Reasoning, (April 2021)
