Hun-Seok Kim is an associate professor at the University of Michigan, Ann Arbor. His research focuses on system analysis, novel algorithms, and efficient VLSI architectures for low-power/high-performance wireless communication, signal processing, computer vision, and machine learning systems.

HTNN (Heterogeneous Transform Domains Neural Network) is a new class of transform domain deep neural networks, where convolution operations are replaced by element-wise multiplications in heterogeneous transform domains. To reduce the network complexity, this framework learns sparse-orthogonal weights in heterogeneous transform domains co-optimized with a hardware-efficient accelerator architecture to minimize the overhead of handling sparse weights. Furthermore, sparse-orthogonal weights are non-uniformly quantized with canonical-signed-digit (CSD) representations to substitute multiplications with simpler additions. The proposed approach reduces the complexity by a factor of 4.9 – 6.8 × without compromising the DNN accuracy compared to equivalent CNNs that employ sparse (pruned) weights.