87 citations · 294 across the 41 of their papers we have counts for
4 papers · 1 filter
Detection and Mitigation of Rare Subclasses in Deep Neural Network Classifiers
Colin Paterson, Radu Calinescu, Chiara Picardi
Regions of high-dimensional input spaces that are underrepresented in training datasets reduce machine-learnt classifier performance, and may lead to corner cases and unwanted bias…
Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challenges
Rob Ashmore, Radu Calinescu, Colin Paterson
Machine learning has evolved into an enabling technology for a wide range of highly successful applications. The potential for this success to continue and accelerate has placed ma…
Risk Structures: Towards Engineering Risk-aware Autonomous Systems
Mario Gleirscher
Inspired by widely-used techniques of causal modelling in risk, failure, and accident analysis, this work discusses a compositional framework for risk modelling. Risk models captur…
Perpetual Assurances for Self-Adaptive Systems
Danny Weyns, Nelly Bencomo, Radu Calinescu +10
Providing assurances for self-adaptive systems is challenging. A primary underlying problem is uncertainty that may stem from a variety of different sources, ranging from incomplet…