AQC- Applied Quantum Computing Group
We advance AI with quantum computing to build simpler, and highly-generalizable clinical AI models focusing on methods including novel spatial neural networks, quantum neural networks and quantum learning
The Applied Quantum Computing Group focuses on three main research pillars: a) Developing novel spatial neural networks to minimize the number of trainable parameters compared to conventional NNs and to objectively increase interpretability & explainability of these models for future clinical adoption; b) Develop so-called variational quantum-classical systems where a classical AI model is trained with quantum learning to dramatically minimize the number of unknown parameters to train, thereby allowing it to be applicable on small data; c) Develop and evaluate the added value of quantum convolutional neural networks in terms of model simplicity and generalizability compared to conventional AI models focusing on medical image analysis
AQC Group:
Lead: Laszlo Papp