6 papers
Benchmarking Ultra-Low-Power NPUs
Josh Millar, Yushan Huang, Sarab Sethi +2
Efficient on-device neural network (NN) inference offers predictable latency, improved privacy and reliability, and lower operating costs for vendors than cloud-based inference. Th…
Towards Low-Energy Adaptive Personalization for Resource-Constrained Devices
Yushan Huang, Josh Millar, Yuxuan Long +2
The personalization of machine learning (ML) models to address data drift is a significant challenge in the context of Internet of Things (IoT) applications. Presently, most approa…
Low-Energy On-Device Personalization for MCUs
Yushan Huang, Ranya Aloufi, Xavier Cadet +3
Microcontroller Units (MCUs) are ideal platforms for edge applications due to their low cost and energy consumption, and are widely used in various applications, including personal…
Towards Machine Learning and Inference for Resource-constrained MCUs
Yushan Huang, Hamed Haddadi
Machine learning (ML) is moving towards edge devices. However, ML models with high computational demands and energy consumption pose challenges for ML inference in resource-constra…
Information Theory Inspired Pattern Analysis for Time-series Data
Yushan Huang, Yuchen Zhao, Alexander Capstick +3
Current methods for pattern analysis in time series mainly rely on statistical features or probabilistic learning and inference methods to identify patterns and trends in the data.…
Using Entropy Measures for Monitoring the Evolution of Activity Patterns
Yushan Huang, Yuchen Zhao, Hamed Haddadi +1
In this work, we apply information theory inspired methods to quantify changes in daily activity patterns. We use in-home movement monitoring data and show how they can help indica…