Diwanshi Gupta
Papers
1
Total Citations
28
H-Index
1
About
Diwanshi Gupta is a researcher at the intersection of deep learning and image processing, with a particular focus on developing efficient neural network architectures for visual data. Her most cited work, "Validation of Random Dataset Using an Efficient CNN Model Trained on MNIST Handwritten Dataset" (2019, 28 citations), addresses a fundamental challenge in the field: ensuring that deep learning models trained on standard benchmarks like MNIST can generalize effectively to random or unseen datasets. This contribution is critical for applications in robotics, medical imaging, and security surveillance, where model reliability is paramount. By demonstrating how convolutional neural networks can be validated against diverse inputs, Gupta’s research helps bridge the gap between controlled experimental settings and real-world deployment. Her work underscores the importance of robust model validation, a key concern for practitioners aiming to deploy AI in safety-critical environments. With her focus on abstraction and representation learning, Gupta continues to advance the practical utility of deep learning, making her research valuable for students and engineers seeking to build more trustworthy computer vision systems.
Research Focus
Key Achievements
Top Papers
- 1