Amanpreet Kaur
Papers
1
Total Citations
2
H-Index
1
About
Amanpreet Kaur is a researcher specializing in machine learning and computer vision, with a particular focus on deep learning architectures for pattern recognition. Her most-cited work, "Recognition of Handwritten Digits Using Convolutional Neural Network in Python and Comparison of Performance for Various Hidden Layers" (2023), demonstrates her expertise in applying convolutional neural networks (CNNs) to classic image classification challenges. In this study, Kaur systematically evaluates how varying the number of hidden layers affects CNN accuracy on the MNIST dataset, providing practical insights for optimizing network design. While her citation count stands at 2, this work represents a foundational contribution to accessible, Python-based implementations of neural networks, making complex concepts more approachable for students and practitioners. Kaur’s research bridges the gap between theoretical deep learning and real-world application, offering reproducible methodologies that advance the field of handwritten digit recognition. Her work is particularly valuable for those exploring the trade-offs between model complexity and performance in computer vision tasks.
Research Focus
Key Achievements
Top Papers
- 1