A team at Terra Quantum AG designed a parallel hybrid quantum neural network and demonstrated that their model is “a powerful tool for quantum machine learning.” This research was published Oct. 9 in Intelligent Computing, a Science Partner Journal. Hybrid quantum neural networks typically consist of both a quantum layer and a classical layer, and the authors focused on parallel hybrid quantum neural networks. The training results demonstrate that the hybrid model can outperform either its quantum layer or its classical layer, and is more adaptable to complex problems and new datasets. The quantum layer maps the smooth periodical parts, while the classical multi-layered perceptron fills in the irregular additions of noise.
