AI Circuits & Systems

Developing revolutionary hardware architectures and intelligent circuit designs specifically optimized for artificial intelligence applications. Our research encompasses energy-efficient AI accelerators, neural processing units, and cutting-edge machine learning hardware.

Research Overview

Our AI circuits and systems research is at the forefront of developing specialized hardware architectures that enable efficient artificial intelligence computation. We focus on creating innovative solutions that bridge the gap between algorithmic requirements and hardware constraints in modern AI applications.

Core Innovation Areas

We specialize in neuromorphic computing architectures, in-memory computing solutions, and ultra-low-power AI accelerators that enable intelligent processing at the edge while maintaining high performance and energy efficiency.

Our multidisciplinary approach combines deep learning algorithms with advanced semiconductor technologies, creating hardware-software co-designed solutions that unlock new possibilities in autonomous systems, smart sensors, and intelligent edge devices.

Advanced AI algorithm for deep learning and machine learning.

Key Research Topics

Explore our specialized research areas that are revolutionizing AI hardware and intelligent systems

🔧

Machine Learning Hardware

Creating domain-specific architectures for various ML algorithms including CNNs, RNNs, and transformers. Research includes in-memory computing, near-data processing, and hardware-software co-design optimization.

📱

Edge AI Computing

Ultra-low-power AI processors for edge devices and IoT applications. Focus on energy-efficient inference engines, dynamic voltage scaling, and adaptive computing techniques for battery-powered intelligent systems.

🔬

Neuromorphic Circuits

Bio-inspired computing architectures that mimic neural networks in hardware. Research includes spiking neural networks, memristive devices, and event-driven processing for ultra-efficient AI computation.

Real-World Applications

Our AI circuits and systems research enables breakthrough applications across diverse industries

🤖

AI computing IC for Autonomous Vehicles

Real-time object detection, path planning, and sensor fusion systems for self-driving cars

📷

Spike Neural Network IC and Systems

High-performance image processing and pattern recognition for surveillance and medical imaging

💊

Healthcare AI

Wearable health monitors, diagnostic imaging, and personalized medical treatment systems

Current Research Projects

🚀

Ultra-Efficient Edge AI Chip

Developing a sub-1W AI accelerator capable of running complex neural networks on battery-powered devices. Features include dynamic precision scaling, adaptive clocking, and intelligent power gating for maximum energy efficiency.

Status: Silicon Validation

⚙️

In-Memory AI Computing

Revolutionary compute-in-memory architecture using resistive RAM arrays for neural network weight storage and multiplication. Eliminates data movement overhead for dramatic energy savings in AI workloads.

Status: Prototype Testing

🎯

Adaptive AI Hardware Platform

Reconfigurable AI accelerator that dynamically adapts its architecture based on the neural network topology and computational requirements. Features runtime optimization and workload-specific acceleration.

Status: System Integration