Related papers: Fast Evaluation of Low-Thrust Transfers via Deep N…

As autonomous systems increasingly rely on Deep Neural Networks (DNN) to implement the navigation pipeline functions, uncertainty estimation methods have become paramount for estimating confidence in DNN predictions. Bayesian Deep Learning…

In this work, we propose a novel machine learning approach to compute the optimal transport map between two continuous distributions from their unpaired samples, based on the DeepParticle methods. The proposed method leads to a min-min…

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…

Multi-Task Learning (MTL) has shown its importance at user products for fast training, data efficiency, reduced overfitting etc. MTL achieves it by sharing the network parameters and training a network for multiple tasks simultaneously.…

A numerical optimization study of minimum-fuel Earth-based orbital transfers from low-Earth orbit (LEO) to either medium-Earth orbit (MEO), high-Earth orbit (HEO), or geostationary orbit (GEO), is performed. Various values of maximum…

The record-breaking performance of deep neural networks (DNNs) comes with heavy parameterization, leading to external dynamic random-access memory (DRAM) for storage. The prohibitive energy of DRAM accesses makes it non-trivial to deploy…

Deep neural networks (DNNs) offer a real-time solution for the inversion of borehole resistivity measurements to approximate forward and inverse operators. It is possible to use extremely large DNNs to approximate the operators, but it…

Deep convolutional neural networks (DCNNs) have attracted much attention in remote sensing recently. Compared with the large-scale annotated dataset in natural images, the lack of labeled data in remote sensing becomes an obstacle to train…

Trajectory optimization of low-thrust perturbed orbit rendezvous is a crucial technology for space missions in low Earth orbits, which is difficult to solve due to its initial value sensitivity, especially when the transfer trajectory has…

The rise of deep learning has led to various successful attempts to apply deep neural networks (DNNs) for important networking tasks such as intrusion detection. Yet, running DNNs in the network control plane, as typically done in existing…

Radiation exposure in positron emission tomography (PET) imaging limits its usage in the studies of radiation-sensitive populations, e.g., pregnant women, children, and adults that require longitudinal imaging. Reducing the PET radiotracer…

Transfer learning plays a key role in modern data analysis when: (1) the target data are scarce but the source data are sufficient; (2) the distributions of the source and target data are heterogeneous. This paper develops an interpretable…

This paper is concerned with ranking many pre-trained deep neural networks (DNNs), called checkpoints, for the transfer learning to a downstream task. Thanks to the broad use of DNNs, we may easily collect hundreds of checkpoints from…

Transfer learning have been frequently used to improve deep neural network training through incorporating weights of pre-trained networks as the starting-point of optimization for regularization. While deep transfer learning can usually…

Machine learning inference is increasingly being executed locally on mobile and embedded platforms, due to the clear advantages in latency, privacy and connectivity. In this paper, we present approaches for online resource management in…

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…

The recent success of Deep Neural Networks (DNNs) has drastically improved the state of the art for many application domains. While achieving high accuracy performance, deploying state-of-the-art DNNs is a challenge since they typically…

Optimally designing molten salt applications requires knowledge of their thermophysical properties, but existing databases are incomplete, and experiments are challenging. Ideal mixing and Redlich-Kister models are computationally cheap but…

The minimum-fuel low-thrust transfer between circular orbits is formulated using the Edelbaum's averaged dynamics with the addition of the nodal precession due to the first zonal term. The extremal analysis shows that an optimal transfer is…

Distributed Deep Neural Network (DNN) training is a technique to reduce the training overhead by distributing the training tasks into multiple accelerators, according to a parallelization strategy. However, high-performance compute and…