Interferometric Neural Networks
This work proposes a novel paradigm for neural networks that could impact fields like quantum computing and photonics, though it appears incremental in its current applications.
The paper tackles the problem of building neural networks without classical layers by introducing interferometric neural networks, which can be implemented on quantum computers or photonic chips, and demonstrates their applicability in combinatorial optimization, image classification with accuracies of 93% and 83%, and image generation.
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.