Related papers: On the Performance of Practical Ultra-Dense Networ…
U-Nets are a go-to, state-of-the-art neural architecture across numerous tasks for continuous signals on a square such as images and Partial Differential Equations (PDE), however their design and architecture is understudied. In this paper,…
Including information from additional spectral bands (e.g., near-infrared) can improve deep learning model performance for many vision-oriented tasks. There are many possible ways to incorporate this additional information into a deep…
The network structure of an urban transportation system has a significant impact on its traffic performance. This study uses network indicators along with several traffic performance measures including speed, trip length, travel time, and…
Deep learning vision systems are widely deployed across applications where reliability is critical. However, even today's best models can fail to recognize an object when its pose, lighting, or background varies. While existing benchmarks…
Network intrusions have become a significant threat in recent years as a result of the increased demand of computer networks for critical systems. Intrusion detection system (IDS) has been widely deployed as a defense measure for computer…
Modern probabilistic regressors often remain overconfident under distribution shift. Functional Distribution Networks (FDN) place input-conditioned distributions over network weights, producing predictive mixtures whose dispersion adapts to…
In automated driving, object detection is crucial for perceiving the environment. Although deep learning-based detectors offer high performance, their black-box nature complicates safety assurance. We propose a novel methodology to analyze…
Reliability is of paramount importance for the physical layer of wireless systems due to its decisive impact on end-to-end performance. However, the uncertainty of prevailing deep learning (DL)-based physical layer algorithms is hard to…
Accurate 3D object detection is a critical component of autonomous driving, enabling vehicles to perceive their surroundings with precision and make informed decisions. LiDAR sensors, widely used for their ability to provide detailed 3D…
The performance of a wireless sensor network (WSN) depends fundamentally on how its various parameters are configured under different link quality conditions. Surprisingly, even though WSNs have been extensively researched, there still…
Supervised deep learning models require significant amount of labeled data to achieve an acceptable performance on a specific task. However, when tested on unseen data, the models may not perform well. Therefore, the models need to be…
Image recognition tasks typically use deep learning and require enormous processing power, thus relying on hardware accelerators like GPUs and TPUs for fast, timely processing. Failure in real-time image recognition tasks can occur due to…
In 5G wireless communication, Intelligent Transportation Systems (ITS) and automobile applications, such as autonomous driving, are widely examined. These applications have strict requirements and often require high Quality of Service…
Statistically independent or positively correlated fading models are usually applied to compute the average performance of wireless communications. However, there exist scenarios with negative dependency and it is therefore of interest how…
Deep Neural Networks (DNNs) have already become a crucial computational approach to revealing the spatial patterns in the human brain; however, there are three major shortcomings in utilizing DNNs to detect the spatial patterns in…
The employment of partial zero-forcing (PZF) receivers at the base stations represents an efficient and low-complexity technique for uplink interference management in cellular networks. In this paper, we focus on the performance analysis of…
Natural Language Inference is a challenging task that has received substantial attention, and state-of-the-art models now achieve impressive test set performance in the form of accuracy scores. Here, we go beyond this single evaluation…
Previous work has established that neural network-based node embeddings return different outcomes when trained with identical parameters on the same dataset, just from using different training seeds. Yet, it has not been thoroughly analyzed…
Densification of the network deployment, for example by adding new sectors or sites within an existing mobile communication network, has traditionally been an efficient way to improve the system coverage and capacity. That will be the case…
Deep neural networks (DNNs) have provided brilliant performance across various tasks. However, this success often comes at the cost of unnecessarily large model sizes, high computational demands, and substantial memory footprints.…