Ali Jahanshahi

Papers

Total Citations

H-Index

About

Ali Jahanshahi is a researcher specializing in hardware acceleration for deep learning, with a particular focus on deploying convolutional neural networks (CNNs) on resource-constrained embedded systems. His work sits at the intersection of computer vision, FPGA design, and energy-efficient computing — a critical frontier as artificial intelligence increasingly moves toward edge devices with limited power and memory budgets. Jahanshahi's most notable contribution is **Inf4Edge** (2021), an automated framework for generating energy-efficient CNN inference accelerators tailored specifically for edge-embedded FPGAs. This work, which has garnered 10 citations, addresses one of the central challenges in embedded AI: making computationally intensive CNN inference practical without sacrificing performance. Building on this, his earlier work **TinyCNN** (2019) introduced a modular, lightweight CNN accelerator architecture designed for embedded FPGAs, demonstrating his sustained commitment to making deep learning accessible on constrained hardware platforms. Together, these contributions reflect a coherent research vision: democratizing intelligent computing at the edge by bridging the gap between powerful neural network models and the practical realities of embedded hardware. His work is particularly relevant for researchers and engineers working on IoT, autonomous systems, and real-time embedded AI applications.