HyungWon Kim

Brain Floating Point Precision for Object Detector

2023

As the size of the deep neural network (DNN) model increases, the memory usage and computational time also increase. Deeper neural network models require huge memory size and high computational power. For edge devices, it …

Reevaluating the Potential of a Vanilla Transformer Encoder for Unsupervised Time Series Anomaly Detection in Sensor Applications

2025 · Sensors

Sensors generate extensive time series data across various domains, and effective methods for detecting anomalies in such data are still in high demand. Unsupervised time series anomaly detection provides practical approaches to addressing the challenges …