능동적 즉시 대응 및 빠른 학습이 가능한 적응형 경량 엣지 연동분석 기술개발

Members

• Jong-Ryul Lee, Junyong Park, Jiyeon Kim, Yong-Ju Lee, Yong-Hyuk Moon (Project Leader)

Challenges

• Competitions for building the most efficient model that solves the target task to the specified quality level.

Research (Wiki)

• Efficient deep learning techniques for improving model performance by understanding neural networks

Applications

• Target use cases (Edge based object detection and action recognition for smart farm and city)

Source

• nn-arch(neural architecture search), nn-comp(neural network compression), nn-infer(inference runtime)

Acknowledgement

This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No. 2021-0-00907, Development of Adaptive and Lightweight Edge-Collaborative Analysis Technology for Enabling Proactively Immediate Response and Rapid Learning).