Related papers: Learning the Noise of Failure: Intelligent System …

Learning with noisy labels has aroused much research interest since data annotations, especially for large-scale datasets, may be inevitably imperfect. Recent approaches resort to a semi-supervised learning problem by dividing training…

Machine learning has become prevalent across a wide variety of applications. Unfortunately, machine learning has also shown to be susceptible to deception, leading to errors, and even fatal failures. This circumstance calls into question…

Large language models (LLMs) are increasingly used as automated judges and synthetic labelers, especially in low-label settings. Yet these systems are stochastic and often overconfident, which makes deployment decisions difficult when…

Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. However, the quality of data labels is a concern because of the lack of high-quality labels in many real-world scenarios. As noisy…

Autonomous robots deal with unexpected scenarios in real environments. Given input images, various visual perception tasks can be performed, e.g., semantic segmentation, depth estimation and normal estimation. These different tasks provide…

Unit testing is crucial for software development and maintenance. Effective unit testing ensures and improves software quality, but writing unit tests is time-consuming and labor-intensive. Recent studies have proposed deep learning (DL)…

Reliability of machine learning evaluation -- the consistency of observed evaluation scores across replicated model training runs -- is affected by several sources of nondeterminism which can be regarded as measurement noise. Current…

Automatically detecting and recovering from failures is an important but challenging problem for autonomous robots. Most of the recent work on learning to plan from demonstrations lacks the ability to detect and recover from errors in the…

Large language models (LLMs) have achieved top results in recent machine translation evaluations, but they are also known to be sensitive to errors and perturbations in their prompts. We systematically evaluate how both humanly plausible…

Deep learning faces a formidable challenge when handling noisy labels, as models tend to overfit samples affected by label noise. This challenge is further compounded by the presence of instance-dependent noise (IDN), a realistic form of…

Providing guarantees on the safe operation of robots against edge cases is challenging as testing methods such as traditional Monte-Carlo require too many samples to provide reasonable statistics. Built upon recent advancements in…

Measurement noise is an integral part while collecting data of a physical process. Thus, noise removal is a necessary step to draw conclusions from these data, and it often becomes quite essential to construct dynamical models using these…

Identifying logical errors in complex, incomplete or even contradictory and overall heterogeneous data like students' experimentation protocols is challenging. Recognizing the limitations of current evaluation methods, we investigate the…

Learning with noisy labels is a vital topic for practical deep learning as models should be robust to noisy open-world datasets in the wild. The state-of-the-art noisy label learning approach JoCoR fails when faced with a large ratio of…

AI systems deployed in the real world must contend with distractions and out-of-distribution (OOD) noise that can destabilize their policies and lead to unsafe behavior. While robust training can reduce sensitivity to some forms of noise,…

In the realm of amateur radio, the effective classification of signals and the mitigation of noise play crucial roles in ensuring reliable communication. Traditional methods for signal classification and noise reduction often rely on manual…

Image classification systems recently made a giant leap with the advancement of deep neural networks. However, these systems require an excessive amount of labeled data to be adequately trained. Gathering a correctly annotated dataset is…

Rapid progress in imitation learning, foundation models, and large-scale datasets has led to robot manipulation policies that generalize to a wide-range of tasks and environments. However, rigorous evaluation of these policies remains a…

Learning-based navigation systems are widely used in autonomous applications, such as robotics, unmanned vehicles and drones. Specialized hardware accelerators have been proposed for high-performance and energy-efficiency for such…

A robot's actions are inherently stochastic, as its sensors are noisy and its actions do not always have the intended effects. For this reason, the agent language Golog has been extended to models with degrees of belief and stochastic…