Proceedings ArticleDOI
Challenges in Using Neural Networks in Safety-Critical Applications
Reads0
Chats0
TLDR
It is concluded that only the most valuable implementations of NNs should be considered as meaningful to implement in safety-critical systems.Abstract:
In this paper, we discuss challenges when using neural networks (NNs) in safety-critical applications. We address the challenges one by one, with aviation safety in mind. We then introduce a possible implementation to overcome the challenges. Only a small portion of the solution has been implemented physically and much work is considered as future work. Our current understanding is that a real implementation in a safety-critical system would be extremely difficult. Firstly, to design the intended function of the NN, and secondly, designing monitors needed to achieve a deterministic and fail-safe behavior of the system. We conclude that only the most valuable implementations of NNs should be considered as meaningful to implement in safety-critical systems.read more
Citations
More filters
Journal ArticleDOI
DeepVigor: Vulnerability Value Ranges and Factors for DNNs' Reliability Assessment
TL;DR: DeepVigor as mentioned in this paper proposes a fine-grained, metric-oriented, and accelerator-agnostic method called DeepVigor that provides vulnerability value ranges for DNN neurons' outputs.
Proceedings ArticleDOI
ADIMA: Automatic Configuration by Peripheral Detection and Adaptive Distributed Task Execution for Integrated Modular Avionics Platforms
TL;DR: In this paper , a static feed-forward neural network is used to detect and utilize a very simple peripheral, like an LED, for commercial off-the-shelf IMA devices and thus enable a plug-and-fly system.
Journal ArticleDOI
Detection of out-of-distribution samples using binary neuron activation patterns
TL;DR: In this paper , the authors proposed a method for OOD detection based on neuron activation patterns (NAP) in ReLU-based architectures, which does not introduce a high computational overhead due to the binary representation of the activation patterns extracted from convolutional layers.
Proceedings ArticleDOI
Image Synthesisation and Data Augmentation for Safe Object Detection in Aircraft Auto-landing System.
Journal ArticleDOI
A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networks
TL;DR: In this article , the authors conduct a systematic literature review (SLR) on the reliability assessment methods of DNNs to collect relevant research works as much as possible, present a categorization of them, and address the open challenges.
References
More filters
Proceedings ArticleDOI
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
TL;DR: In this article, the authors show that it is possible to produce images that are completely unrecognizable to humans, but that state-of-the-art DNNs believe to be recognizable objects with 99.99% confidence.
Posted Content
Virtual Worlds as Proxy for Multi-Object Tracking Analysis
TL;DR: This work proposes an efficient real-to-virtual world cloning method, and validate the approach by building and publicly releasing a new video dataset, called "Virtual KITTI", automatically labeled with accurate ground truth for object detection, tracking, scene and instance segmentation, depth, and optical flow.
Proceedings ArticleDOI
VirtualWorlds as Proxy for Multi-object Tracking Analysis
TL;DR: In this article, the authors proposed an efficient real-to-virtual world cloning method, and validated their approach by building and publicly releasing a new video dataset, called "Virtual KITTI" 1, automatically labeled with accurate ground truth for object detection, tracking, scene and instance segmentation, depth, and optical flow.
Journal ArticleDOI
Application of the residue number system to reduce hardware costs of the convolutional neural network implementation
TL;DR: A convolutional neural network architecture in which the neural network is divided into hardware and software parts to increase performance and reduce the cost of implementation resources is proposed.
Proceedings ArticleDOI
MODTRAN6: a major upgrade of the MODTRAN radiative transfer code
Alexander Berk,Patrick Conforti,R. Kennett,Timothy Perkins,Frederick Hawes,Jeannette van den Bosch +5 more
TL;DR: TheMODTRAN6 radiative transfer (RT) code is a major advancement over earlier versions of the MODTRAN atmospheric transmittance and radiance model and includes a line-by-line algorithm for high resolution RT calculations as well as coupling to optical scattering codes for easy implementation of custom aerosols and clouds.