University of Bremen

About: University of Bremen is a education organization based out in Bremen, Germany. It is known for research contribution in the topics: Population & Context (language use). The organization has 14563 authors who have published 37279 publications receiving 970381 citations. The organization is also known as: Universität Bremen.

Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks

Abstract: We present an approach for the verification of feed-forward neural networks in which all nodes have a piece-wise linear activation function. Such networks are often used in deep learning and have been shown to be hard to verify for modern satisfiability modulo theory (SMT) and integer linear programming (ILP) solvers.

Laser-induced incandescence : recent trends and current questions

Abstract: This paper provides an overview of a workshop focused on fundamental experimental and theoretical aspects of soot measurements by laser-induced incandescence (LII). This workshop was held in Duisburg, Germany in September 2005. The goal of the workshop was to review the current understanding of the technique and identify gaps in this understanding associated with experimental implementation, model descriptions, and signal interpretation. The results of this workshop suggest that uncertainties in the understanding of this technique are sufficient to lead to large variability among model predictions from different LII models, among measurements using different experimental approaches, and between modeled and measured signals, even under well-defined conditions. This article summarizes the content and conclusions of the workshop, discusses controversial topics and areas of disagreement identified during the workshop, and highlights recent important references related to these topics. It clearly demonstrates that despite the widespread application of LII for soot-concentration and particle-size measurements there is still a significant lack in fundamental understanding for many of the underlying physical processes.

Solving inverse problems using data-driven models

Abstract: Recent research in inverse problems seeks to develop a mathematically coherent foundation for combining data-driven models, and in particular those based on deep learning, with domain-specific knowledge contained in physical–analytical models. The focus is on solving ill-posed inverse problems that are at the core of many challenging applications in the natural sciences, medicine and life sciences, as well as in engineering and industrial applications. This survey paper aims to give an account of some of the main contributions in data-driven inverse problems.