Modular AI Verification and Visualisation (MAIVV)
(2021-2025)
(2021-2025)
Modular AI Verification and Visualisation (MAIVV) is led by Professor Rosemary Monahan and Professor Barak A. Pearlmutter in the Dept. of Computer Science and Hamilton Institute at Maynooth University . The project is funded from December 2021 until November 2025, hiring two three-year postdoctoral researchers and one PhD student over the four years.
Our overall goal is to provide scalable techniques for software development that guarantee software dependability.
Some information on our research follows at the links below:
- NeuralVizVR: An Open source platform to improve neural network interpretability and analysis by leveraging immersive 3D visualization, interactive exploration, and advanced AI-assisted techniques, making complex models more accessible and understandable to a wide range of users.
- Comparing Differentiable Logics for Learning with Logical Constraints: A promising approach for creating machine learning models that inherently satisfy constraints after training is to encode background knowledge as explicit logical constraints that guide the learning process via so-called differentiable logics. Here, we experimentally compare and evaluate various logics from the literature, presenting our findings and highlighting open problems for future work.
- Creating a Formally Verified Neural Network for Autonomous Navigation: We present our experience of a case study exploring the design and training of a neural network on a custom dataset for vision-based autonomous navigation.