Related papers: A Scenario-Based Functional Testing Approach to Im…
We propose Deep Companion Learning (DCL), a novel training method for Deep Neural Networks (DNNs) that enhances generalization by penalizing inconsistent model predictions compared to its historical performance. To achieve this, we train a…
Reinforcement learning (RL) is attracting attention as an effective way to solve sequential optimization problems that involve high dimensional state/action space and stochastic uncertainties. Many such problems involve constraints…
Checkpoints play an important role in training long running machine learning (ML) models. Checkpoints take a snapshot of an ML model and store it in a non-volatile memory so that they can be used to recover from failures to ensure rapid…
Most existing failure detection algorithms rely on statistical methods, and very few use machine learning (ML). This paper explores the viability of ML in the field of failure detection: is it possible to implement an ML-based detector that…
Owing to their remarkable learning capabilities and performance in real-world applications, the use of machine learning systems based on Neural Networks (NNs) has been continuously increasing. However, various case studies and empirical…
Substantial efforts have been made on improving the generalization abilities of deep neural networks (DNNs) in order to obtain better performances without introducing more parameters. On the other hand, meta-learning approaches exhibit…
Even as deep neural networks (DNNs) have achieved remarkable success on vision-related tasks, their performance is brittle to transformations in the input. Of particular interest are semantic transformations that model changes that have a…
Model Checking is widely applied in verifying complicated and especially concurrent systems. Despite of its popularity, model checking suffers from the state space explosion problem that restricts it from being applied to certain systems,…
Context: Deep Neural Networks (DNNs) are increasingly deployed in critical applications, where resilience against adversarial inputs is paramount. However, whether coverage-based or confidence-based, existing test prioritization methods…
Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In order to cope with a wide range of reverberations in…
As ultracold atom experiments become highly controlled and scalable quantum simulators, they require sophisticated control over high-dimensional parameter spaces and generate increasingly complex measurement data that need to be analyzed…
In recent years, deep reinforcement learning has emerged as a technique to solve closed-loop flow control problems. Employing simulation-based environments in reinforcement learning enables a priori end-to-end optimization of the control…
Deep neural networks (DNNs) are instrumental in realizing complex perception systems. As many of these applications are safety-critical by design, engineering rigor is required to ensure that the functional insufficiency of the DNN-based…
Countless domains rely on Machine Learning (ML) models, including safety-critical domains, such as autonomous driving, which this paper focuses on. While the black box nature of ML is simply a nuisance in some domains, in safety-critical…
Deep neural networks can be unreliable in the real world when the training set does not adequately cover all the settings where they are deployed. Focusing on image classification, we consider the setting where we have an error distribution…
Several datasets have recently been constructed to expose brittleness in models trained on existing benchmarks. While model performance on these challenge datasets is significantly lower compared to the original benchmark, it is unclear…
This paper describes a practical approach of using supervised machine learning (ML) models to assist safety investigators to classify aviation occurrences into either incident or serious incident categories. Our implementation currently…
In an ever expanding set of research and application areas, deep neural networks (DNNs) set the bar for algorithm performance. However, depending upon additional constraints such as processing power and execution time limits, or…
With the rapid development of Deep Learning, more and more applications on the cloud and edge tend to utilize large DNN (Deep Neural Network) models for improved task execution efficiency as well as decision-making quality. Due to memory…
Scenario-based development and test processes are a promising approach for verifying and validating automated driving functions. For this purpose, scenarios have to be generated during the development process in a traceable manner. In early…