Mohammad Soltanian

Papers

Total Citations

H-Index

About

Mohammad Soltanian is a researcher whose work sits at the intersection of efficient machine learning and human-computer interaction, with a particular focus on speech command recognition. His most cited paper, "Speech Command Recognition in Computationally Constrained Environments with a Quadratic Self-Organized Operational Layer" (2022, 11 citations), addresses a critical challenge in deploying AI on resource-limited devices. Soltanian’s major contribution lies in developing lightweight neural architectures that maintain high accuracy while drastically reducing memory and energy consumption—a breakthrough for robotic and embedded systems where computational resources are scarce. By introducing a quadratic self-organized operational layer, he demonstrates how to squeeze complex deep learning models into constrained environments without sacrificing performance. This work has direct implications for edge computing and real-time voice-controlled applications, making AI more accessible and sustainable. Soltanian’s research bridges the gap between theoretical efficiency and practical deployment, earning recognition among peers working on low-power AI systems. His focus on computationally frugal models positions him as a key contributor to the next generation of intelligent, energy-aware devices.