Search

Quantum-inspired evolutionary algorithm (QEA) has proved to be an effective method to design neural networks with few connections and high classification performance. When a quantum-inspired evolutionary neural network (QENN) converges in the training phase, subsequent training is fruitless and time-wasting. Therefore, it is important to control the number of generations of QENN. The analysis on the convergence property of quantum bit evolution can contribute to designing a safe termination criterion that can always be reached. This paper proposes an appropriate termination criterion based on the average convergence rate (ACR). Experiments on classification tasks are conducted to demonstrate the effectiveness of our method. The results show that the termination criterion based on ACR can duly stop the training process of QENN and overcome the limitations of the termination criterion based on the probability of generating the best solution (PBS). [ABSTRACT FROM AUTHOR]

In recent times, deep learning models have achieved state-of-the-art performances in image classification. However, the classification and generalization ability of most achievements have highly relied on the availability of large-scale accurate labeled training data, which are time-consuming, laborious, and expensive to collect. Moreover, in the generalizing process of deep learning models, the noisy labels are the challenges for multi-category classification. Hence, it is essential to explore effective methods that can efficiently and correctly train deep models under label noise to conduct multi-category classification. This paper proposes using robust binary loss functions to train deep models under label noise to address this problem. Specifically, we suggest handling the K -class classification task by using K binary classifiers, which can be completed by a joint adoption of multi-category large margin classification approaches, e.g., Pairwise-Comparison (PC) or One-versus-All (OVA). We also theoretically demonstrate that our method is inherently tolerant to label noise by using symmetric binary loss functions in multi-category classification tasks. Moreover, we designed a truncated CCE loss to combine with the proposed losses to improve the learning ability. Finally, we test our method on three different benchmark datasets with different types of label noise. The experimental results have clearly confirmed the effectiveness of our method, which can reduce the negative effect of noisy labels and improve the generalization ability. [ABSTRACT FROM AUTHOR]

Generative adversarial network (GAN) has shown profound power in machine learning. It inspires many researchers from other fields to create powerful tools for various tasks, including quantum state preparation, quantum circuit translation, and so on. It is known as classical techniques cannot efficiently simulate the quantum system, and the existing works haven't investigated the quantum version of maximum mean discrepancy as the metric in learning models and applied it to quantum data. In this paper, we propose a metric named quantum maximum mean discrepancy (qMMD), which can be used to measure the distance between quantum data in Hilbert space. Based on the qMMD, we then design a quantum generative adversarial model, named qMMD-GAN, under the hybrid quantum–classical methods. We also provide the construction of qMMD-GAN that can be easily implemented on a quantum device. We demonstrate the power of our qMMD-GAN by applying it to a crucial real-world application that is generating an unknown quantum state. Our numerical experiments show that qMMD-GAN has a competitive performance compared to existing results. We believe that the hybrid-based models will not only be applied to physics research but provide a new direction for improving classical data processing tasks. [ABSTRACT FROM AUTHOR]