On the one hand, artificial neural networks have many successful applications in the field of machine learning and optimization. On the other hand, interferometers are integral parts of any field that deals with waves such as optics, astronomy, and quantum physics. Here, we introduce neural networks composed of interferometers and then build generative adversarial networks from them. Our networks do not have any classical layer and can be realized on quantum computers or photonic chips. We demonstrate their applicability for combinatorial optimization, image classification, and image generation. For combinatorial optimization, our network consistently converges to the global optimum or remains within a narrow range of it. In multi-class image classification tasks, our networks achieve accuracies of 93% and 83%. Lastly, we show their capability to generate images of digits from 0 to 9 as well as human faces.

翻译：一方面，人工神经网络在机器学习和优化领域已有诸多成功应用；另一方面，干涉仪是任何涉及波动（如光学、天文学和量子物理学）领域的核心组成部分。本文提出由干涉仪构成的神经网络，并进一步构建基于此类网络的生成对抗网络。我们的网络不含任何经典层，可在量子计算机或光子芯片上实现。我们展示了其在组合优化、图像分类和图像生成中的适用性：在组合优化任务中，网络始终收敛至全局最优解或保持在其狭窄范围内；在多类别图像分类任务中，网络分别实现了93%和83%的准确率；最后，我们展示了其生成0至9数字图像及人脸图像的能力。