相关论文: nn-dependability-kit: Engineering Neural Networks …

The work presented in this paper is part of a proposed framework as complete and rigorous as possible for the design of complex systems. The methodological framework used is System Engineering, which is a methodological approach to control…

Making AI safe and dependable requires the generation of dependable models and dependable execution of those models. We propose redundant execution as a well-known technique that can be used to ensure reliable execution of the AI model.…

This work focuses on the design of a deep learning-based autonomous driving system deployed and tested on the real-world MIT Racecar to assess its effectiveness in driving scenarios. The Deep Neural Network (DNN) translates raw image inputs…

This paper aims to enhance the computational efficiency of safety verification of neural network control systems by developing a guaranteed neural network model reduction method. First, a concept of model reduction precision is proposed to…

Novel computing hardwares are necessary to keep up with today's increasing demand for data storage and processing power. In this research project, we turn to the brain for inspiration to develop novel computing substrates that are…

The use of deep neural networks (DNNs) in safety-critical applications like mobile health and autonomous driving is challenging due to numerous model-inherent shortcomings. These shortcomings are diverse and range from a lack of…

Aiming for a higher economic efficiency in manufacturing, an increased degree of automation is a key enabler. However, assessing the technical feasibility of an automated assembly solution for a dedicated process is difficult and often…

Deep neural networks can be trained to be efficient and effective controllers for dynamical systems; however, the mechanics of deep neural networks are complex and difficult to guarantee. This work presents a general approach for providing…

Testing of autonomous systems is extremely important as many of them are both safety-critical and security-critical. The architecture and mechanism of such systems are fundamentally different from traditional control software, which appears…

Safe learning is central to AI-enabled robots where a single failure may lead to catastrophic results. Barrier-based method is one of the dominant approaches for safe robot learning. However, this method is not scalable, hard to train, and…

Uncertainty in decision-making is crucial in the machine learning model used for a safety-critical system that operates in the real world. Therefore, it is important to handle uncertainty in a graceful manner for the safe operation of the…

Autonomous driving demands an integrated approach that encompasses perception, prediction, and planning, all while operating under strict energy constraints to enhance scalability and environmental sustainability. We present Spiking…

Deploying machine learning models in safety-related do-mains (e.g. autonomous driving, medical diagnosis) demands for approaches that are explainable, robust against adversarial attacks and aware of the model uncertainty. Recent deep…

Maintaining an acceptable level of quality of service in modern complex systems is challenging, particularly in the presence of various forms of uncertainty caused by changing execution context, unpredicted events, etc. Although…

Performance of trained neural network (NN) models, in terms of testing accuracy, has improved remarkably over the past several years, especially with the advent of deep learning. However, even the most accurate NNs can be biased toward a…

The success of deep neural networks (DNNs) is attributable to three factors: increased compute capacity, more complex models, and more data. These factors, however, are not always present, especially for edge applications such as autonomous…

Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental challenges. One of these open problems is the inherent lack…

We introduce an open-source toolkit for neural machine translation (NMT) to support research into model architectures, feature representations, and source modalities, while maintaining competitive performance, modularity and reasonable…

Motivated by the fragility of neural network (NN) controllers in safety-critical applications, we present a data-driven framework for verifying the risk of stochastic dynamical systems with NN controllers. Given a stochastic control system,…

With the advancement of deep learning technology, neural networks have demonstrated their excellent ability to provide accurate predictions in many tasks. However, a lack of consideration for neural network calibration will not gain trust…