QUANT-PHLGDec 29, 2019

QDNN: DNN with Quantum Neural Network Layers

arXiv:1912.12660v220 citations
Originality Incremental advance
AI Analysis

This work addresses the problem of enhancing neural network capabilities for researchers in quantum computing and machine learning, though it appears incremental as it builds on classical DNNs with quantum layers.

The paper introduces QDNN, a quantum extension of classical deep neural networks that can uniformly approximate any continuous function and has greater representation power, achieving high accuracy in an image classification experiment.

In this paper, we introduce a quantum extension of classical DNN, QDNN. The QDNN consisting of quantum structured layers can uniformly approximate any continuous function and has more representation power than the classical DNN. It still keeps the advantages of the classical DNN such as the non-linear activation, the multi-layer structure, and the efficient backpropagation training algorithm. Moreover, the QDNN can be used on near-term noisy intermediate-scale quantum processors. A numerical experiment for image classification based on quantum DNN is given, where a high accuracy rate is achieved.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes