Abstract Deep Neural Networks (DNNs) learn representation from data with an impressive capability, and brought important breakthroughs for processing images, time-series, natural …
Large language models (LLMs) have shown excellent performance on various tasks, but the astronomical model size raises the hardware barrier for serving (memory size) and slows …
G Xiao, J Lin, M Seznec, H Wu… - International …, 2023 - proceedings.mlr.press
Large language models (LLMs) show excellent performance but are compute-and memory- intensive. Quantization can reduce memory and accelerate inference. However, existing …
CY Wang, A Bochkovskiy… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Real-time object detection is one of the most important research topics in computer vision. As new approaches regarding architecture optimization and training optimization are …
On-device training enables the model to adapt to new data collected from the sensors by fine-tuning a pre-trained model. Users can benefit from customized AI models without having …
R David, J Duke, A Jain… - Proceedings of …, 2021 - proceedings.mlsys.org
Abstract We introduce TensorFlow (TF) Micro, an open-source machine learning inference framework for running deep-learning models on embedded systems. TF Micro tackles the …
Tiny deep learning on microcontroller units (MCUs) is challenging due to the limited memory size. We find that the memory bottleneck is due to the imbalanced memory distribution in …
The advancements in machine learning (ML) opened a new opportunity to bring intelligence to the low-end Internet-of-Things (IoT) nodes, such as microcontrollers. Conventional ML …
Executing machine learning workloads locally on resource constrained microcontrollers (MCUs) promises to drastically expand the application space of IoT. However, so-called …