The Distinguished Lecture on “Neural-Network-Based Non-linearity Suppression Mechanism for High-speed Analog-to-Digital Converters (ADCs)” will take place as follows:
Date: 29 April 2024 (Monday)
Time: 11:00 a.m. – 12:30 p.m.
Venue: Research Building N21, 3/F, Room 3004
The speaker is:
Prof. TANG He, Professor, University of Electronic Science and Technology of China
The Lecture is:
Neural-Network-Based Non-linearity Suppression Mechanism for High-speed Analog-to-Digital Converters (ADCs)
Abstract:
Non-linearities, e.g., IGE, interleaved mismatches, high-order non-linear errors, are the primary factors that deteriorate the dynamic performance of high-speed analog-to-digital converters (ADCs). Conventional solutions are to apply calibration techniques, such as analog circuit compensation, digital correlation, digital statistic-based method, for non-linearity suppression. However, conventional approaches are highly dependent on specific types of errors and ADCs’ structures, causing high circuit complexity and limitation in practical applications. Moreover, as sample rate increasing, non-linearities are hard to be accurately modeled, and higher order and non-analytical non-linear errors play more important roles. Therefore, a new paradigm of non-linearity suppression mechanism is very much required.
We propose the neural-network-based (NN) non-linearity suppression mechanism and verify it by circuit implementation. We present the idea of signal Vector Recovery Mapping (VRM), the NN calibration algorithm, the training and verification framework for NN calibration model, and the realization of NN calibrator circuits. Our research work shows some impressive measurement results in which harmonic distortions and spurs are effectively suppressed, and SFDR/SNDR are largely improved for different types of ADCs (pipelined, P-SAR, and time-interleaved).
Biography:
Prof. TANG He received the B.S.E.E. degree from the University of Electronic Science and Technology of China, Chengdu, China, in 2005, the M.S. degree in electrical and computer engineering from Illinois Institute of Technology, Chicago, in 2007, and the Ph.D. degree in electrical engineering from University of California, Riverside, U.S.A., in 2010. From 2010 to 2012, he was with OmniVision Technologies Inc., in Santa Clara, California, as an Analog IC Designer, where he worked on high-speed mixed-signal circuit design. Since 2012, he has been an Associate Professor and subsequently a Professor at University of Electronic Science and Technology of China (UESTC), Chengdu, China. He has authored or coauthored over 50 papers. His current research interests focus on high-speed ADCs, e.g., Pipelined ADC, TI ADCs, P-SAR ADCs, new paradigm of nonlinearity suppression algorithm and high precision SAR ADCs. He is now the director of Mixed-signal and SoC Design Center in UESTC. Prof. Tang has served on IEEE CAS Analog Signal Processing Technical Committee (ASPTC) from 2013 to 2018, been awarded the National Talent Program and awarded the First Prize of Science and Technology Progress Award of Sichuan Province..
For more details, kindly find the event poster, abstract and bio.
