Capsule networks, which incorporate the paradigms of connectionism and symbolism, have brought fresh insights into artificial intelligence. The capsule, as the building block of capsule networks, is a group of neurons represented by a vector to encode different features of an entity. The information is extracted hierarchically through capsule layers via routing algorithms. Here, we introduce a quantum capsule network (dubbed QCapsNet) together with an efficient quantum dynamic routing algorithm. To benchmark the performance of the QCapsNet, we carry out extensive numerical simulations on the classification of handwritten digits and symmetry-protected topological phases, and show that the QCapsNet can achieve an enhanced accuracy and outperform conventional quantum classifiers evidently. We further unpack the output capsule state and find that a particular subspace may correspond to a human-understandable feature of the input data, which indicates the potential explainability of such networks. Our work reveals an intriguing prospect of quantum capsule networks in quantum machine learning, which may provide a valuable guide towards explainable quantum artificial intelligence.
翻译:Capsule 网络包含连接和象征主义的范式,它为人工智能带来了新的洞察力。作为胶囊网络的构件,胶囊是一组以矢量为代表的神经元,可以对实体的不同特征进行编码。信息是通过输胶层通过路由算法逐级提取的。在这里,我们引入了量子胶网(dubbed QCapsNet),以及高效量子动态路由算法。为了对QCapsNet的性能进行基准,我们进行了大量数字模拟,对手写数字和对称保护的表层阶段进行分类,并显示QCapsNet可以明显地实现更高的准确性和超出常规量分级。我们进一步解了输出囊状态,发现特定的子空间可能与输入数据的人类可理解特征相对应,这表明这种网络的潜在解释性。我们的工作揭示了定量胶囊网络在量子机器学习中的令人感兴趣的前景,这可以为可解释的量子人工智能提供宝贵的指导。