Quanvolutional neural networks: powering image recognition with quantum circuits

By Maxwell P. Henderson, Samriddhi Shakya, S. Pradhan, Tristan Cook. Quantum Machine Intelligence, 2019

525 citations recorded by the source corpus.

Convolutional neural networks (CNNs) have rapidly risen in popularity for many machine learning applications, particularly in the field of image recognition. Much of the benefit generated from these networks comes from their ability to extract features from the data in a hierarchical manner. These features are extracted using various transformational layers, notably the convolutional layer which gives the model its name. In this work, we introduce a new type of transformational layer called a quantum convolution, or quanvolutional layer. Quanvolutional layers operate on input data by locally transforming the data using a number of random quantum circuits, in a way that is similar to the transformations performed by random convolutional filter layers. Provided these quantum transformations produce meaningful features for classification purposes, then this algorithm could be of practical use for near-term quantum computers as it requires small quantum circuits with little to no error correction. In this work, we empirically evaluated the potential benefit of these quantum transformations by comparing three types of models built on the MNIST dataset: CNNs, quantum convolutional neural networks (QNNs), and CNNs with additional non-linearities introduced. Our results showed that the QNN models had both higher test set accuracy as well as faster training compared with the purely classical CNNs.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/5672e42c3b1436f668b63287a8a4e6c96c8e69d9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Maria Schuld
2. Josh A. Izaac
3. Nathan Killoran
4. Thomas R. Bromley
5. Song Han
6. Yujun Lin
7. Andrea Mari
8. L. Kim

In Electrical and Electronic Engineering

1. Song Han
2. David Zhigang Pan
3. Frederic T. Chong
4. Hanrui Wang

Citations in the corpus

• QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits (2021, background): “, quantum classifier [19], quantum convolution [27], and quantum Boltzmann machine [2], etc.”
• Quantum convolutional neural network for classical data classification (2021, methodology): “Following the nomenclature provided in Henderson et al. (2020), we refer to this approach as quanvolutioanl neural network to distinguish it from QCNN.”
• Transfer learning in hybrid classical-quantum neural networks (2019, background): “We would like to mention that also other alternative approaches for dealing with large images have been recently proposed [21, 29, 35, 42].”
• Robust data encodings for quantum classifiers (2020, unknown): “For the processing step (3), there have been many proposed QNN architectures in recent literature, including quantum convolutional neural networks [63, 64], strongly entangling ansätze [33], and more [35, 65].”
• Parameterized quantum circuits as machine learning models (2019, unknown): “Another proposal that is based on random encoder circuits, but inspired by the convolutional filters used in neural networks, is the quanvolutional network by Henderson et al. [20].”