Weidong Cao
George Washington University, DC·Engineering
Analog and mixed-signal chips connect electronics to the physical world: sensors, radios and power circuits. Yet engineers still design them largely by hand, which is slow and costly.
- Fields
Engineering
Computer Science
- Topics
electronic design automation
analog circuit design
analog/mixed-signal
- Grants
- 3 known grants, through Aug 2029
What they work on
- Build AnalogEDA-Hub, an open-source platform with multi-modal datasets, learning-based tools and standard design environments, so researchers can benchmark AI methods for analog circuit design in a reproducible way.
- Create shareable datasets and AI models for analog/mixed-signal chip design, and develop ways to deploy them on shared computing infrastructure while keeping confidential design data private.
- Analyze data-leakage and model-exploitation attacks on AI chip-design tools, develop defenses, and release the resulting tools and benchmarks in the OpenAMS platform.
- Develop an end-to-end architecture for in-sensor compression and feature extraction that works with many AI models, and build compressive sensor hardware to support it.
- Create cross-stack design tools and sensor prototypes, and test whether they improve efficiency for real-time machine vision and continuous physiological monitoring.
More about the research
Artificial intelligence (AI) could automate this work, but it needs large, shared datasets that companies are reluctant to expose. Sensor chips also send huge amounts of raw data off-chip for AI processing, which wastes energy. The projects aim to build open tools, data and hardware that make chip design and edge computing faster, safer and more efficient.
Why it matters
Faster, automated analog chip design could cut the cost and time of making chips used in communications, healthcare and computing. Privacy-preserving tools could let chip companies collaborate on AI-based design without exposing their confidential data. Sensors that process data at the point of capture could make wearable health monitors and machine vision systems use less energy, respond faster and better protect privacy.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
CICI: UCSS: Trustworthy Cyberinfrastructure-Enabled Data-Driven Electronic Design Automation for Collaborative Design of Analog/Mixed-Signal Integrated Circuits
NSF · Sep 2026 – Aug 2029
Collaborative Research: SHF: SensABridge: Learnable Sensor-AI Bridge for Ubiquitous Edge Intelligent Processing
NSF · Aug 2026 – Jul 2029
Elements: AnalogEDA-Hub: At-Scale Analog Circuit Electronic Design Automation with An Open and Efficient Platform
NSF · May 2026 – Apr 2029
Closest labs
Jiaqi Gu
Arizona State University Campus Immersion, AZ·Engineering·Early-career
Develop a learned electromagnetic solver, a machine-learning model of how light moves through photonic devices, and a circuit-level co-simulator for fast simulation of mixed electronic-photonic chips.
Shantanu Chakrabartty
Washington University in St Louis, MO·Engineering
Model single-electron transport across a Fowler-Nordheim quantum tunneling barrier as the equivalent of a neural spike in NeuroSA, a spiking architecture where neuron firing thresholds follow tunneling physics.
Farimah Farahmandi
University of Florida, FL·Engineering·Early-career
Build a comprehensive database of security properties and rules for system-on-chip (SoC) designs, using AI to help collect and organize them for use in pre-fabrication security checks.
The school
George Washington University: 13 labs on PI Pages, $382M a year on research, 225 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.