Dan Su

About

Dan Su’s research centers on the hardware implementation of neural networks, with a particular focus on real-time control and robotics applications. His major contributions include pioneering the FPGA-based parallel implementation of specialized neural architectures, such as the Radial Basis Function (RBF) network and the Cerebellar Model Articulation Controller (CMAC). By designing these networks for on-chip learning and parallel processing, Su has addressed critical challenges in deploying neural networks for practical, time-sensitive tasks—bridging the gap between theoretical algorithms and physical hardware. His 2008 work on RBF network control via FPGA, cited 13 times, demonstrates the viability of neural controllers in robotics, while his 2007 CMAC implementation, with 6 citations, further advances on-chip learning for adaptive systems. These achievements highlight Su’s role in making neural networks more efficient and deployable in embedded systems, offering a pathway for students and researchers interested in neuromorphic engineering, real-time control, and the intersection of AI with hardware design.

Research Focus

Key Achievements

Top Papers

1. 1
   Neural control based on RBF network implemented on FPGA

   13 citations · 2008
2. 2
   FPGA Parallel Implementation of CMAC Type Neural Network with on Chip Learning

   6 citations · 2007

Key Collaborators

Contact & Links