Papers
3
Total Citations
90
H-Index
3
About
Shadman Sakib is a researcher whose work centers on deep learning, artificial neural networks, and computer vision, with a particular focus on practical applications of Convolutional Neural Networks (CNNs). His research has made meaningful contributions to the field of handwritten digit recognition, exploring how CNN architectures implemented in Python with TensorFlow can be optimized through variations in hidden layer configurations to achieve superior classification accuracy. Sakib's most influential work, published in 2019, investigates the performance dynamics of CNN models applied to handwritten digit datasets, systematically comparing how different hidden layer depths and structures affect recognition outcomes. This paper has garnered 77 citations, reflecting its value as an accessible yet rigorous reference for students and practitioners entering the deep learning space. His broader publication portfolio on the same theme, accumulating additional citations across related studies, underscores a consistent commitment to making neural network methodologies transparent and reproducible. By grounding theoretical deep learning concepts in hands-on implementation, Sakib's research serves as an important educational resource, bridging the gap between foundational machine learning principles and real-world AI applications. His work continues to be cited by researchers and students exploring neural network optimization and image recognition tasks.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3