Quanvolutional neural networks: powering image recognition with quantum circuits
- PDF / 588,171 Bytes
- 9 Pages / 595.224 x 790.955 pts Page_size
- 69 Downloads / 253 Views
RESEARCH ARTICLE
Quanvolutional neural networks: powering image recognition with quantum circuits Maxwell Henderson1
· Samriddhi Shakya1 · Shashindra Pradhan1 · Tristan Cook1
Received: 22 May 2019 / Accepted: 9 January 2020 © Springer Nature Switzerland AG 2020
Abstract 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. Keywords Quantum computing · Machine learning · Deep neural networks
1 Introduction The field of quantum machine learning (QML) has experienced rapid growth over the past few years, as evidenced by the rapid increase in impactful QML papers (Jordan 2011). Several excellent papers (Dunjko and Briegel 2018; Ciliberto et al. 2018; Dunjko et al. 2016; Perdomo-Ortiz et al. 2017; Biamonte et al. 2018) encapsulate the current state of the QML field. Machine learning algorithms tend to give probabilistic results and contain correlated components but at the same time suffer computational bottlenecks due to the curse of dimensionality. Similarly, quantum computers by their very nature provide probabilistic results upon measurement and are formed from intrinsically coupled quantum systems, which can provide potentially exponential speedups due to their ability to perform massively parallel computations on the superposition of quantum states. While Maxwell Henderson
[email protected] 1
Rigetti Computing, 2919 Seventh St, Berkeley, CA 94710, USA
quantum computers are by no means expected to replace classical computing, they have the potential to be powerful components in an overall machine learning application pipeline. Our research focuses on a novel quantum algorithm which falls squarely into the regime of “hybrid classicalquantum” algorithms, extending the
Data Loading...
