Search
Search Results
-
-
Smell and Taste-Based Interactions Enabled Through Advances in Digital Technology
Innovations around smell and taste interfaces are quickly emerging in the literature and practice, they include fully controllable sensory delivery... -
Some Remarks About Dependent Type Theory
The goal of this chapter is to describe a calculus designed in 1984/1985. This calculus was obtained by applying the ideas introduced by N.G. de... -
ChatGPT in the Loop: A Natural Language Extension for Domain-Specific Modeling Languages
This paper presents an approach to no-code development based on the interplay of formally defined (graphical) Domain-Specific Languages and informal,... -
Continuous Engineering for Trustworthy Learning-Enabled Autonomous Systems
Learning-enabled autonomous systems (LEAS) use machine learning (ML) components for essential functions of autonomous operation, such as perception... -
Benchmarks: Semantic Segmentation Neural Network Verification and Objection Detection Neural Network Verification in Perceptions Tasks of Autonomous Driving
The verification of the security of neural networks is cruicial, especially for the field of autonomous driving. Although there are currently... -
Welcome Remarks from AISoLA 2023/Track C2 Chairs
We are happy to present the proceedings of AISoLA’s Track C2: Verification meets Learning and Statistics. -
gRoMA: A Tool for Measuring the Global Robustness of Deep Neural Networks
Deep neural networks (DNNs) are at the forefront of cutting-edge technology, and have been achieving remarkable performance in a variety of complex... -
Towards a Formal Account on Negative Latency
Low latency communication is a major challenge when humans have to be integrated into cyber physical systems with mixed realities. Recently, the... -
Shielded Learning for Resilience and Performance Based on Statistical Model Checking in Simulink
Safety, resilience and performance are crucial properties in intelligent hybrid systems, in particular if they are used in critical infrastructures... -
What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety-Critical Systems
Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses... -
Machine-Code Generation
The intermediate language we have used in Chap. 6 is quite low-level and similar to the type of machine code you can find on modern RISC processors,... -
Functions
In Chap. 6 we have shown how to translate the body of a single function. Function calls and returns were... -
Deep Neural Networks, Explanations, and Rationality
“Rationality” is the principle that humans make decisions on the basis of step-by-step (algorithmic) reasoning using systematic rules of logic. An... -
Benchmark: Neural Network Malware Classification
As malware threats continue to increase in both complexity and sophistication, the adoption of advanced detection methods, such as deep neural... -
Benchmark: Object Detection for Maritime Search and Rescue
We propose an object detection system for maritime search and rescue as a benchmark problem for verification of neural networks (VNN). The model to... -
Large Language Model Assisted Software Engineering: Prospects, Challenges, and a Case Study
Large language models such as OpenAI’s GPT and Google’s Bard offer new opportunities for supporting software engineering processes. Large language... -
Formal XAI via Syntax-Guided Synthesis
In this paper, we propose a novel application of syntax-guided synthesis to find symbolic representations of a model’s decision-making process,... -
Benchmark: Remaining Useful Life Predictor for Aircraft Equipment
We propose a predictive maintenance application as a benchmark problem for verification of neural networks (VNN). It is a deep learning based... -
Scopes and Symbol Tables
An important concept in programming languages is the ability to name items such as variables, functions and types. Each such named item will have a...