most citedAdoption and Effects of Software Engineering Best Practices in Machine Learning

97 citations · 109 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV202011 cited

Adversarial Examples on Object Recognition: A Comprehensive Survey

Alex Serban, Erik Poll, Joost Visser

Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small pertur…

cs.SE20201 cited

GraphRepo: Fast Exploration in Software Repository Mining

Alex Serban, Magiel Bruntink, Joost Visser

Mining and storage of data from software repositories is typically done on a per-project basis, where each project uses a unique combination of data schema, extraction tools, and (…

cs.LG2020

Learning to Learn from Mistakes: Robust Optimization for Adversarial Noise

Alex Serban, Erik Poll, Joost Visser

Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustn…

cs.SE2020

Towards Using Probabilistic Models to Design Software Systems with Inherent Uncertainty

Alex Serban, Erik Poll, Joost Visser

The adoption of machine learning (ML) components in software systems raises new engineering challenges. In particular, the inherent uncertainty regarding functional suitability and…

cs.SE202097 cited

Adoption and Effects of Software Engineering Best Practices in Machine Learning

Alex Serban, Koen van der Blom, Holger Hoos +1

The increasing reliance on applications with machine learning (ML) components calls for mature engineering techniques that ensure these are built in a robust and future-proof manne…

cs.AI2019

Counterexample-Guided Strategy Improvement for POMDPs Using Recurrent Neural Networks

Steven Carr, Nils Jansen, Ralf Wimmer +3

We study strategy synthesis for partially observable Markov decision processes (POMDPs). The particular problem is to determine strategies that provably adhere to (probabilistic) t…