Amin Majd
Papers
2
Total Citations
21
H-Index
2
About
Amin Majd is a researcher at the forefront of embedded artificial intelligence and optimization algorithms. His work primarily focuses on designing efficient neural network architectures for autonomous systems, particularly in the challenging domain of stereo vision. Majd’s most cited paper, "Designing Compact Convolutional Neural Network for Embedded Stereo Vision Systems" (2018, 15 citations), addresses a critical bottleneck in autonomous robotics and self-driving cars: enabling real-time depth perception on resource-constrained hardware. By developing compact CNNs, he has made stereo vision—a technique that extracts depth, color, and shape—more practical for embedded platforms, impacting fields from surgical robots to household utensils. Beyond deep learning, Majd has contributed to metaheuristic optimization, as seen in his work "Multi-population parallel imperialist competitive algorithm for solving systems of nonlinear equations" (2016, 6 citations). This research tackles NP-hard problems in economics, engineering, and mechanics by enhancing the efficiency of evolutionary algorithms. His interdisciplinary approach bridges theoretical optimization with real-world embedded systems, making his work valuable for students and engineers developing next-generation autonomous technologies.
Research Focus
Key Achievements
Top Papers
- 1
- 2