Proceedings of tinyML Research Symposium – 2022
Millimeter-Scale Ultra-Low-Power Imaging System for Intelligent Edge Monitoring – Andrea Bejarano-Carbo, Hyochan An, Kyojin Choo, Shiyu Liu, Dennis Sylvester, David Blaauw, Hun-Seok Kim [arxiv] [paper]
How to Manage Tiny Machine Learning at Scale – An Industrial Perspective – Haoyu Ren, Darko Anicic, Thomas Runkler [arxiv] [paper]
Distributed On-Sensor Compute System for AR/VR Devices: A Semi-Analytical Simulation Framework for Power Estimation – Jorge Gomez, Saavan Patel, Syed Shakib Sarwar, Ziyun Li, Raffaele Capoccia, Zhao Wang, Reid Pinkham, Andrew Berkovich, Tsung-Hsun Tsai, Barbara De Salvo, Chiao Liu
[arxiv] [paper]
IMU Preintegrated Features for Efficient Deep Inertial Odometry – R. Khorrambakht, H. Damirchi, H. D. Taghirad [arxiv] [paper]
LDP: Learnable Dynamic Precision for Efficient Deep Neural Network Training and Inference – Zhongzhi Yu, Yonggan Fu, Shang Wu, Mengquan Li, Haoran You, Yingyan Lin [arxiv] [paper]
PocketNN: Integer-only Training and Inference of Neural Networks via Direct Feedback Alignment and Pocket Activations in Pure C++ – Jaewoo Song, Fangzhen Lin [arxiv] [paper]
tinyMAN: Lightweight Energy Manager using Reinforcement Learning for Energy Harvesting Wearable IoT Devices – Toygun Basaklar, Yigit Tuncel, Umit Y. Ogras [arxiv] [paper]
Delta Keyword Transformer: Bringing Transformers to the Edge through Dynamically Pruned Multi-Head Self-Attention – Zuzana Jelčicová, Marian Verhelst [arxiv] [paper]
Toward Compact Deep Neural Networks via Energy-Aware Pruning – Seul-Ki Yeom, Kyung-Hwan Shim, Jee-Hyun Hwang [arxiv] [paper]
Improving the Energy Efficiency and Robustness of tinyML Computer Vision using Log-Gradient Input Images – Qianyun Lu, Boris Murmann [arxiv] [paper]
An Empirical Study of Low Precision Quantization for TinyML – Shaojie Zhuo, Hongyu Chen, Ramchalam Kinattinkara Ramakrishnan, Tommy Chen, Chen Feng, Yicheng Lin, Parker Zhang, Liang Shen [arxiv] [paper]
Power-of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks – Dominika Przewlocka-Rus, Syed Shakib Sarwar, H. Ekin Sumbul, Yuecheng Li, Barbara De Salvo [arxiv] [paper]
A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices – Shijin Duan, Xiaolin Xu, Shaolei Ren
[arxiv] [paper]
TinyM^2Net: A Flexible System Algorithm Co-designed Multimodal Learning Framework for Tiny Devices – Hasib-Al Rashid, Pretom Roy Ovi, Carl Busart, Aryya Gangopadhyay, Tinoosh Mohsenin [arxiv] [paper]