Architecture and independence controller for deep learning in safety critical applications

2019 ◽  
pp. 1131-1142
Author(s):  
Ulrich Bodenhausen
Keyword(s):  
Deep Learning ◽  
Safety Critical

Impact of Deep Learning Techniques in IoT

2021 ◽  
pp. 196-226
Author(s):  
Chandra Vadhana ◽  
Shanthi Bala P. ◽  
Immanuel Zion Ramdinthara
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Learning Models ◽  
Related Services ◽  
Safety Critical ◽  
The Neural Network ◽  
Learning Techniques ◽  
Iot Devices ◽  
The Impact ◽  
Level Performance

Deep learning models can achieve more accuracy sometimes that exceed human-level performance. It is crucial for safety-critical applications such as driverless cars, aerospace, defence, medical research, and industrial automation. Most of the deep learning methods mimic the neural network. It has many hidden layers and creates patterns for decision making and it is a subset of machine learning that performs end-to-end learning and has the capability to learn unsupervised data and also provides very flexible, learnable framework for representing the visual and linguistic information. Deep learning has greatly changed the way and computing devices processes human-centric content such as speech, image recognition, and natural language processing. Deep learning plays a major role in IoT-related services. The amalgamation of deep learning to the IoT environment makes the complex sensing and recognition tasks easier. It helps to automatically identify patterns and detect anomalies that are generated by IoT devices. This chapter discusses the impact of deep learning in the IoT environment.

scholarly journals TSInsight: A Local-global Attribution Framework for Interpretability in Time Series Data

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7373
Author(s):  
Shoaib Ahmed Siddiqui ◽  
Dominique Mercier ◽  
Andreas Dengel ◽  
Sheraz Ahmed
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Time Series Data ◽  
Series Data ◽  
Time Series Models ◽  
Learning Methods ◽  
Deep Time ◽  
Safety Critical ◽  
Fine Tune ◽  
Output Space

With the rise in the employment of deep learning methods in safety-critical scenarios, interpretability is more essential than ever before. Although many different directions regarding interpretability have been explored for visual modalities, time series data has been neglected, with only a handful of methods tested due to their poor intelligibility. We approach the problem of interpretability in a novel way by proposing TSInsight, where we attach an auto-encoder to the classifier with a sparsity-inducing norm on its output and fine-tune it based on the gradients from the classifier and a reconstruction penalty. TSInsight learns to preserve features that are important for prediction by the classifier and suppresses those that are irrelevant, i.e., serves as a feature attribution method to boost the interpretability. In contrast to most other attribution frameworks, TSInsight is capable of generating both instance-based and model-based explanations. We evaluated TSInsight along with nine other commonly used attribution methods on eight different time series datasets to validate its efficacy. The evaluation results show that TSInsight naturally achieves output space contraction; therefore, it is an effective tool for the interpretability of deep time series models.

A Safe, Secure, and Predictable Software Architecture for Deep Learning in Safety-Critical Systems

2020 ◽  
Vol 12 (3) ◽  
pp. 78-82 ◽  
Author(s):  
Alessandro Biondi ◽  
Federico Nesti ◽  
Giorgiomaria Cicero ◽  
Daniel Casini ◽  
Giorgio Buttazzo
Keyword(s):  
Deep Learning ◽  
Software Architecture ◽  
Critical Systems ◽  
Safety Critical ◽  
Safety Critical Systems

Deep Learning

2009 ◽  
Author(s):  
Stellan Ohlsson
Keyword(s):  
Deep Learning

Intelligence artificielle : le futur de l’Orthodontie ?

2019 ◽  
Vol 53 (3) ◽  
pp. 281-294
Author(s):  
Jean-Michel Foucart ◽  
Augustin Chavanne ◽  
Jérôme Bourriau
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Intelligence Artificielle ◽  
Set Up

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.

Sign in / Sign up

Export Citation Format

Share Document