Da Eun Shim
Papers
1
Total Citations
4
H-Index
1
About
Da Eun Shim’s research centers on efficient deep neural network (DNN) inference for resource-constrained edge devices, with a focus on image recognition and parallel computing. Her most cited work, “LCP: A Low-Communication Parallelization Method for Fast Neural Network Inference in Image Recognition” (2020, 4 citations), tackles a critical bottleneck in deploying DNNs on robots, autonomous agents, and IoT devices. The method reduces inter-processor communication overhead during inference, enabling faster and more practical edge AI without sacrificing accuracy. This contribution addresses the fundamental tension between the computational demands of modern neural networks and the limited resources of edge hardware. Beyond this paper, Shim’s broader research explores parallelization strategies and low-power inference techniques, positioning her work at the intersection of systems optimization and applied deep learning. Her findings hold promise for real-time applications in autonomous navigation and smart sensing, where latency and energy efficiency are paramount. As edge AI continues to expand, Shim’s contributions offer a pragmatic path toward deploying sophisticated models in the wild.
Research Focus
Key Achievements
Top Papers
- 1