Related papers: Carbon Intensity-Aware Adaptive Inference of DNNs

Neural networks have dramatically increased our capacity to learn from large, high-dimensional datasets across innumerable disciplines. However, their decisions are not easily interpretable, their computational costs are high, and building…

Deep learning for distribution grid optimization can be advocated as a promising solution for near-optimal yet timely inverter dispatch. The principle is to train a deep neural network (DNN) to predict the solutions of an optimal power flow…

While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches. These approaches aim for a carefully…

Computer models play a key role in many scientific and engineering problems. One major source of uncertainty in computer model experiment is input parameter uncertainty. Computer model calibration is a formal statistical procedure to infer…

Deep learning models undergo a significant increase in the number of parameters they possess, leading to the execution of a larger number of operations during inference. This expansion significantly contributes to higher energy consumption…

Residential occupancy detection has become an enabling technology in today's urbanized world for various smart home applications, such as building automation, energy management, and improved security and comfort. Digitalization of the…

For speech recognition, deep neural networks (DNNs) have significantly improved the recognition accuracy in most of benchmark datasets and application domains. However, compared to the conventional Gaussian mixture models, DNN-based…

Deep learning models are being adopted and applied on various critical decision-making tasks, yet they are trained to provide point predictions without providing degrees of confidence. The trustworthiness of deep learning models can be…

The growing demand for the internet of things (IoT) makes it necessary to implement computer vision tasks such as object recognition in low-power devices. Convolutional neural networks (CNNs) are a potential approach for object recognition…

State-of-the-art convolutional neural networks (CNNs) yield record-breaking predictive performance, yet at the cost of high-energy-consumption inference, that prohibits their widely deployments in resource-constrained Internet of Things…

Emerging Artificial Intelligence of Things (AIoT) applications desire online prediction using deep neural network (DNN) models on mobile devices. However, due to the movement of devices, unfamiliar test samples constantly appear,…

Faithful energy reconstruction is foundational for precision neutrino experiments like DUNE, but is hindered by uncertainties in our understanding of neutrino--nucleus interactions. Here, we demonstrate that dense neural networks are very…

Deep neural networks (DNNs) offer significant flexibility and robust performance. This makes them ideal for building not only system models but also advanced neural network controllers (NNCs). However, their high complexity and…

Existing deep neural network (DNN) based wireless localization approaches typically do not capture uncertainty inherent in their estimates. In this work, we propose and evaluate variational and scalable DNN approaches to measure the…

Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification - a critical requirement for real-world applications. Bayesian Neural Networks (BNN) are…

Currently, the world experiences an unprecedentedly increasing generation of application data, from sensor measurements to video streams, thanks to the extreme connectivity capability provided by 5G networks. Going beyond 5G technology,…

We propose a novel method for training a neural network for image classification to reduce input data dynamically, in order to reduce the costs of training a neural network model. As Deep Learning tasks become more popular, their…

Energy-efficient deep neural network (DNN) accelerators are prone to non-idealities that degrade DNN performance at inference time. To mitigate such degradation, existing methods typically add perturbations to the DNN weights during…

Recent advances in deep learning, whether on discriminative or generative tasks have been beneficial for various applications, among which security and defense. However, their increasing computational demands during training and deployment…

The opaque nature of transformer-based models, particularly in applications susceptible to unethical practices such as dark-patterns in user interfaces, requires models that integrate uncertainty quantification to enhance trust in…