Yao Chen is a Postdoc researcher at Advanced Digital Sciences Center (ADSC), Singapore, which is a research center of University of Illinois at Urbana-Champaign (UIUC) based in Singapore. He got his Bachelor and PhD at Nankai University from 2006 to 2016, respectively. His current research Interests including FPGA enabled High Performance Computing, High Level Synthesis, Distributed Systems and Wireless Sensor Networks. Some of his work also related to Internet of Things, Bioinformatics and High Precision/Accuracy Analog ASIC Design. For the details, please refer to https://microideax.github.io/.
The efficacy and effectiveness of Convolutional Neural Networks(CNNs) have been proven in a wide range of machine learning applications. However, the high computational complexity of CNNs presents a critical challenge towards their broader adoption in real-time and power-efficient scenarios. FPGAs are poised to take a significant role for high-performance and energy-efficient computation of CNNs for both mobile (e.g., UAVs, self-driving cars, and IoT devices) and cloud computing domains.
However, implementing an effective CNN system onto FPGAs efficiently remains problematic. The current cloud-based FPGAs with unique design constraints and architectural characteristics remain challenging. The Internet of Thing (IoT) devices, with strict constraints on hardware resources, power budgets, response latency, and manufacturing cost also further increases the difficulties.
To address these challenges, we have several different approaches, which are named as Cloud-DNN, T-DLA and uL2Q. The details will be presented in the talk.