Sumaiya Shomaji
Papers
1
Total Citations
2
H-Index
1
About
Sumaiya Shomaji is a researcher at the intersection of artificial intelligence and resource-constrained computing, with a focus on efficient multi-task learning. Her key contributions lie in developing novel neural architecture search frameworks that optimize deep learning models for real-world applications in healthcare, autonomous systems, and robotics. Shomaji’s most notable work, “Intelligent Layer Sharing (ILASH): A Predictive Neural Architecture Search Framework for Multi-Task Applications,” introduces a pioneering approach to automatically design shared neural network architectures that perform multiple analyses on the same data while minimizing computational overhead. This framework addresses the critical challenge of deploying AI on resource-limited devices, making it highly relevant for edge computing scenarios. Though early in her career, her work has already garnered attention, with her flagship paper accumulating citations and demonstrating the growing demand for efficient multi-tasking AI solutions. Shomaji’s research promises to enable smarter, more sustainable AI systems that can handle complex, simultaneous tasks—from medical image analysis to traffic monitoring—without sacrificing performance or energy efficiency. Her contributions are paving the way for the next generation of adaptive, multi-purpose artificial intelligence.
Research Focus
Key Achievements
Top Papers
- 1