Add to Favourites
To login click here
Researchers at Volkswagen have developed a quantum-inspired hyperparameter optimization technique and a hybrid quantum-classical machine learning model for supervised learning. This technique was benchmarked against standard black-box objective functions and showed reduced expected run times and higher accuracy. It was tested in a car image classification task using a full-scale implementation of the hybrid quantum ResNet model with the tensor trained hyperparameter optimization, resulting in a classification accuracy of 0.97 after 18 iterations, compared to 0.92 after 75 iterations for the classical model.
