UofS Ko Lab
Deep learning and its application research at the University of Saskatchewan.
Welcome
The Ko Lab, led by Prof. Seok-Bum Ko in the Department of Electrical and Computer Engineering and the Division of Biomedical Engineering, designs efficient hardware and algorithms for artificial intelligence. The work runs from the arithmetic circuits inside a processor, through accelerators and compressed models, to deep learning applied in medicine, agriculture and industry.
The question underneath all of it is the same one: how do you get modern AI to run on hardware that is small, cheap and power-constrained, and how do you know you can trust the answer it gives?
Research
Five areas
- Hardware Design for Deep Learning — arithmetic units, accelerators and sparse-network microarchitecture
- Efficient and Compressed AI Models — pruning, quantization and architecture search that fit large models onto edge hardware
- Security, Privacy and Cryptography — differential privacy accelerators, lightweight intrusion detection, AES and post-quantum hardware
- Medical Imaging and Biomedical AI — CT, MRI, ultrasound, X-ray and biomedical signals, tested against the specialists the systems support
- Computer Vision and Applied AI — livestock welfare, crop yield prediction, vehicle inspection and document understanding
The Team
Who works here
Ten people: the supervisor, two postdoctoral fellows, six doctoral researchers and a master's student, working across hardware design, efficient AI, privacy, medical imaging and computer vision.
Each member's page lists their publications, with the key result and a figure from each paper.
Recent Work
Selected 2026 papers
- FlexPWL: a flexible, scalable and multiplier-free approach for activation functions on FPGA. IEEE Transactions on Computers, 2026.
- LYRA: low-frequency rank adaptation via factored DCT coefficients for parameter-efficient fine-tuning of transformers. IEEE Signal Processing Letters, 2026.
- Computer vision system for assessing pig welfare indicators on carcasses. Veterinary and Animal Science, 2026.
- Power-efficient and reconfigurable compute unit for multi-precision AI inference at the edge. IEEE ISCAS, 2026.
- An introduction to AI for clinicians. Interactive Journal of Medical Research, 2026.
All publications, or browse by year: 2026 | 2025 | 2024 | 2023
Get in Touch
Enquiries and graduate study
Prof. Seok-Bum Ko
Email: seokbum.ko@usask.ca
Room 3B48.2, Engineering Building, 57 Campus Drive, Saskatoon, SK
The lab supervises graduate students in electrical and computer engineering and in biomedical engineering. Read the research areas first, then write with your CV and a note on which area interests you.