Mahjabin Oishe
Papers
1
Total Citations
60
H-Index
1
About
Mahjabin Oishe has made impactful contributions at the intersection of deep learning and pattern recognition, with a particular focus on convolutional neural networks (CNNs). Her most cited work, "Study and Observation of the Variations of Accuracies for Handwritten Digits Recognition with Various Hidden Layers and Epochs using Convolutional Neural Network" (2018, 60 citations), systematically investigates how architectural choices—specifically hidden layers and training epochs—influence CNN accuracy for handwritten digit recognition. This research provides practical guidance for optimizing neural network configurations, bridging foundational deep learning theory with real-world applications in medicine, engineering, and natural language processing. Oishe’s work demonstrates the versatility of CNNs across domains, from pattern and sequence recognition to video analysis and spam detection. Her findings have been widely referenced by researchers seeking to improve model performance through systematic hyperparameter tuning. By clarifying how network depth and training duration affect classification accuracy, Oishe has helped advance accessible, reproducible deep learning practices. Her research continues to inform both academic studies and applied AI systems, underscoring the importance of empirical optimization in neural network design.
Research Focus
Key Achievements
Top Papers
- 1