Mohammad Mahmudur Rahman Khan
Papers
1
Total Citations
60
H-Index
1
About
Mohammad Mahmudur Rahman Khan is a researcher whose work sits at the intersection of deep learning and practical pattern recognition applications. His notable 2018 study on handwritten digit recognition using Convolutional Neural Networks (CNNs) demonstrates his commitment to advancing our understanding of how architectural choices — specifically variations in hidden layers and training epochs — influence model accuracy. This foundational contribution has garnered 60 citations, reflecting its value to the broader machine learning community. Khan's research speaks directly to the growing demand for robust deep learning frameworks applicable across diverse domains, including medicine, engineering, natural language processing, video analysis, and spam detection. By systematically investigating the behavioral dynamics of CNNs, he has helped clarify how these powerful models can be optimized for real-world deployment. His work serves as an important reference point for students and practitioners seeking to understand the nuanced relationship between network design and performance outcomes. For emerging researchers navigating the rapidly evolving landscape of artificial intelligence, Khan's empirical and methodical approach offers a valuable model — grounding theoretical deep learning concepts in measurable, reproducible experimental outcomes that advance both academic understanding and applied innovation.
Research Focus
Key Achievements
Top Papers
- 1