Research Interests

Neural Network-Friendly Hardware / Hardware-Friendly Neural Network

Network Compression: Pruning, Quantization
Efficient Sparse Matrix Handling in NN Hardware
Variable-Precision Neural Network Hardware
Multi-bit Neural Network with Bitwise Activation

 


Near-/In-Memory Neural Network Computing

Resistive Memory Based Neural Network Hardware
SRAM based Binary Neural Network Hardware
Mapping Large Neural Network on Memory Arrays
Minimizing the Overhead of Peripheral Circuits(ADC/DAC) for In-Memory DNN Computing
Process-Variation tolerant In-Memory NN Computing
Near-Memory NN Processing in 3D High Bandwidth Memory (HBM)
Spin Device based Neural Network Hardware

 


Spiking Neural Network (SNN) Hardware

FireFly: Large Scale CMOS SNN Hardware
Efficient Synapse Memory Structure
6T SRAM Cell based Integrated Transposable Synapse Memory
Multi-Core SNN Chip Architecture
Supervised Learning in SNN
Convolution Mapping on SNN Hardware

 


Hardware Security IP

CMOS True Random Number Generator (TRNG)
CMOS Physically Unclonable Function (PUF)

 


Device/Circuit Design for Exploratory Technology

Split-Gate Ambipolar Device/Circuit
Negative Transconductance Heterojunction Transistor
Multi-level Metal Interconnection for Organic Device Technology