collaborators

5 papers

cs.LG2021

Dependable Neural Networks Through Redundancy, A Comparison of Redundant Architectures

Hans Dermot Doran, Gianluca Ielpo, David Ganz +1

With edge-AI finding an increasing number of real-world applications, especially in industry, the question of functionally safe applications using AI has begun to be asked. In this…

cs.AR2021

Dynamic Lockstep Processors for Applications with Functional Safety Relevance

Hans Dermot Doran, Timo Lang

Lockstep processing is a recognized technique for helping to secure functional-safety relevant processing against, for instance, single upset errors that might cause faulty executi…

cs.LG2020

Examining Redundancy in the Context of Safe Machine Learning

Hans Dermot Doran, Monika Reif

This paper describes a set of experiments with neural network classifiers on the MNIST database of digits. The purpose is to investigate naïve implementations of redundant architec…

cs.DC2020

Voting Framework for Distributed Real-Time Ethernet based Dependable and Safe Systems

Hans Dermot Doran

In many industrial sectors such as factory automation and process control sensor redundancy is required to ensure reliable and highly-available operation. Measured values from N-re…

cs.HC2020

Conceptual Design of Human-Drone Communication in Collaborative Environments

Hans Dermot Doran, Monika Reif, Marco Oehler +2

Autonomous robots and drones will work collaboratively and cooperatively in tomorrow's industry and agriculture. Before this becomes a reality, some form of standardised communicat…