Evaluating the Trade-offs Between Machine Learning and Deep Learning: A Multi-Dimensional Analysis
Journal of Computer, Software, and Program · 06.03.2025 · 2 (1) · 10-18
DOI: 10.69739/jcsp.v2i1.254 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computer, Software, and Program, online erschienen am 06.03.2025. Verfasst von Nagwa Elmobark. Die Arbeit wurde bisher 8-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The proliferation of artificial intelligence applications necessitates a clear understanding of the fundamental distinctions between Machine Learning (ML) and Deep Learning (DL) approaches. This study presents a systematic comparative analysis through a multi-dimensional evaluation framework. We analyzed 150 implementations across three domains (computer vision, natural language processing, and structured data analysis), evaluating performance metrics, resource utilization, and architectural complexities. Our findings reveal that while DL architectures achieve superior accuracy in complex pattern recognition tasks (mean improvement: 27.3%, p < 0.001), they require substantially higher computational resources (GPU utilization: 89.2% vs. 23.7% for ML). Traditional ML demonstrates notable advantages in scenarios with limited datasets (
Zitieren
APA
Elmobark, N. (2025). Evaluating the Trade-offs Between Machine Learning and Deep Learning: A Multi-Dimensional Analysis. Journal of Computer, Software, and Program, 2(1), 10-18. https://doi.org/10.69739/jcsp.v2i1.254
Vancouver
Elmobark N. Evaluating the Trade-offs Between Machine Learning and Deep Learning: A Multi-Dimensional Analysis. Journal of Computer, Software, and Program. 2025;2(1):10-18. doi:10.69739/jcsp.v2i1.254
BibTeX
@article{Elmobark2025,
author = {Elmobark, Nagwa},
title = {Evaluating the Trade-offs Between Machine Learning and Deep Learning: A Multi-Dimensional Analysis},
journal = {Journal of Computer, Software, and Program},
year = {2025},
volume = {2},
number = {1},
pages = {10--18},
doi = {10.69739/jcsp.v2i1.254}
}
EUVIMED