no code implementations • 22 Jul 2023 • Zexin Li, Xiaoxi He, Yufei Li, Shahab Nikkhoo, Wei Yang, Lothar Thiele, Cong Liu
In this paper, we propose MIMONet, a novel on-device multi-input multi-output (MIMO) DNN framework that achieves high accuracy and on-device efficiency in terms of critical performance metrics such as latency, energy, and memory usage.
no code implementations • 12 Jun 2023 • Wenying Duan, Xiaoxi He, Zimu Zhou, Lothar Thiele, HONG RAO
Spatial-temporal graph models are prevailing for abstracting and modelling spatial and temporal dependencies.
1 code implementation • 22 May 2023 • Olga Saukh, Dong Wang, Xiaoxi He, Lothar Thiele
The obtained subspace is low-dimensional and has a surprisingly simple structure even for complex, non-invertible transformations of the input, leading to an exceptionally high efficiency of subspace-configurable networks (SCNs) when limited storage and computing resources are at stake.
no code implementations • 25 Jun 2022 • Zhongnan Qu, Zimu Zhou, Yongxin Tong, Lothar Thiele
Data collected by IoT devices are often private and have a large diversity across users.
1 code implementation • 22 Feb 2022 • Wenying Duan, Xiaoxi He, Lu Zhou, Lothar Thiele, HONG RAO
In this paper, we propose Hyper Time- Series Forecasting (HTSF), a hypernetwork-based framework for accurate time series forecasting under distribution shift.
no code implementations • 1 Dec 2021 • Yingzhao Lian, Yuning Jiang, Naomi Stricker, Lothar Thiele, Colin N. Jones
The wide adoption of wireless devices in the Internet of Things requires controllers that are able to operate with limited resources, such as battery life.
no code implementations • 5 Aug 2021 • Andres Gomez, Andreas Tretter, Pascal Alexander Hager, Praveenth Sanmugarajah, Luca Benini, Lothar Thiele
By leveraging interkernel data dependencies, these energy-bounded execution cycles minimize the number of system activations and nonvolatile data transfers, and thus the total energy overhead.
no code implementations • 19 Jul 2021 • Matthias Meyer, Michaela Wenner, Clément Hibert, Fabian Walter, Lothar Thiele
Real-world datasets collected with sensor networks often contain incomplete and uncertain labels as well as artefacts arising from the system environment.
2 code implementations • 21 Apr 2021 • Lennart Heim, Andreas Biri, Zhongnan Qu, Lothar Thiele
With the surge of inexpensive computational and memory resources, neural networks (NNs) have experienced an unprecedented growth in architectural and computational complexity.
no code implementations • 6 Jul 2020 • Zhongnan Qu, Cong Liu, Lothar Thiele
Emerging edge intelligence applications require the server to retrain and update deep neural networks deployed on remote edge nodes to leverage newly collected data samples.
2 code implementations • 18 Feb 2020 • Romain Jacob, Licong Zhang, Marco Zimmerling, Jan Beutel, Samarjit Chakraborty, Lothar Thiele
Wirelessly interconnected sensors, actuators, and controllers promise greater flexibility, lower installation and maintenance costs, and higher robustness in harsh conditions than wired solutions.
Networking and Internet Architecture
1 code implementation • CVPR 2020 • Zhongnan Qu, Zimu Zhou, Yun Cheng, Lothar Thiele
We investigate the compression of deep neural networks by quantizing their weights and activations into multiple binary bases, known as multi-bit networks (MBNs), which accelerate the inference and reduce the storage for the deployment on low-resource mobile and embedded platforms.
no code implementations • 23 May 2019 • Xiaoxi He, Dawei Gao, Zimu Zhou, Yongxin Tong, Lothar Thiele
Given a set of deep neural networks, each pre-trained for a single task, it is desired that executing arbitrary combinations of tasks yields minimal computation cost.
no code implementations • 22 Oct 2018 • Matthias Meyer, Timo Farei-Campagna, Akos Pasztor, Reto Da Forno, Tonio Gsell, Jérome Faillettaz, Andreas Vieli, Samuel Weber, Jan Beutel, Lothar Thiele
Decision making at the edge of a wireless sensor network promises fast response times but is limited by the availability of energy, data transfer speed, processing and memory constraints.
no code implementations • NeurIPS 2018 • Xiaoxi He, Zimu Zhou, Lothar Thiele
Future mobile devices are anticipated to perceive, understand and react to the world on their own by running multiple correlated deep neural networks on-device.
no code implementations • 11 Dec 2017 • Matthias Meyer, Jan Beutel, Lothar Thiele
It incorporates the two following novel contributions: First, an audio frame predictor based on a Convolutional LSTM autoencoder is demonstrated, which is used for unsupervised feature extraction.
no code implementations • 28 Sep 2017 • Matthias Meyer, Lukas Cavigelli, Lothar Thiele
Wireless distributed systems as used in sensor networks, Internet-of-Things and cyber-physical systems, impose high requirements on resource efficiency.
no code implementations • 20 Aug 2014 • Pier Stanislao Paolucci, Iuliana Bacivarov, Devendra Rai, Lars Schor, Lothar Thiele, Hoeseok Yang, Elena Pastorelli, Roberto Ammendola, Andrea Biagioni, Ottorino Frezza, Francesca Lo Cicero, Alessandro Lonardo, Francesco Simula, Laura Tosoratto, Piero Vicini
The EURETILE project required the selection and coding of a set of dedicated benchmarks.
no code implementations • 7 May 2013 • Pier Stanislao Paolucci, Iuliana Bacivarov, Gert Goossens, Rainer Leupers, Frédéric Rousseau, Christoph Schumacher, Lothar Thiele, Piero Vicini
Furthermore, EURETILE investigates and implements the innovations for equipping the elementary HW tile with high-bandwidth, low-latency brain-like inter-tile communication emulating 3 levels of connection hierarchy, namely neural columns, cortical areas and cortex, and develops a dedicated cortical simulation benchmark: DPSNN-STDP (Distributed Polychronous Spiking Neural Net with synaptic Spiking Time Dependent Plasticity).