DOCSLIB.ORG

A Simple Quantum Neural Net with a Periodic Activation Function

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
A Simple Quantum Neural Net with a Periodic Activation Function A Simple Quantum Neural Net with a Periodic Activation Function Ammar Daskin Department of Computer Engineering, Istanbul Medeniyet University, Kadikoy, Istanbul, Turkey Email: adaskin25-at-gmail-dot-com Abstract—In this paper, we propose a simple neural net that phase estimation to imitate the output of a classical perceptron requires only O(nlog2k) number of qubits and O(nk) quantum where the binary input is mapped to the second register of the gates: Here, n is the number of input parameters, and k is algorithm and the weights are implemented by phase gates. the number of weights applied to these parameters in the proposed neural net. We describe the network in terms of a The main problem in current quantum learning algorithms is quantum circuit, and then draw its equivalent classical neural to tap the full power of artificial neural networks into the n net which involves O(k ) nodes in the hidden layer. Then, quantum realm by providing robust data mapping algorithms we show that the network uses a periodic activation function from the classical realm to the quantum and processing this of cosine values of the linear combinations of the inputs and data in a nonlinear way similar to the classical neural networks. weights. The backpropagation is described through the gradient descent, and then iris and breast cancer datasets are used for It is shown that a repeat until success circuit can be used to the simulations. The numerical results indicate the network create a quantum perceptron with nonlinear behavior as a main can be used in machine learning problems and it may provide building block of quantum neural nets [22]. It is also explained exponential speedup over the same structured classical neural in Ref.[23] how mapping data into Hilbert space can help for net. kernel based learning algorithms. Index Terms —quantum machine learning, quantum neural The superposition is one of the physical phenomena that networks. allows us to design computationally more efficient quantum Neural networks are composed of many non-linear compo- algorithms. In this paper, we present a quantum neural net by nents that mimic the learning mechanism of a human-brain. fully utilizing the superposition phenomenon. After describing The training in networks is done by adjusting weight constants the network as a quantum circuit, we analyze the quantum state applied to the input parameters. However, the considered of the circuit-output and show that it relates to a neural net numbers of input parameters and the layers in these net- with a periodic activation function involving the cosine values works increase the computational cost dramatically. Quantum of the weighted sum of the input parameters. We then present computers are believed to be more powerful computational the complexity of the network and then show the numerical machines which may allow to solve many intractable problems simulations for two different data sets. in science and engineering. Although building useful quantum computers with many qubits are the main focus of recent I. QUANTUM NEURAL NET experimental research efforts [1], the complete use of these In classical neural networks, linear combinations of input computers are only possible by novel algorithms that provides parameters with different weights are fed into multiple neu- computational speed-up over classical algorithms. rons. The output of each neuron is determined by an activation Although many early efforts to describe quantum perceptron function such as the following one (see Ref.[24] for a smooth arXiv:1804.07633v3 [quant-ph] 17 Jul 2018 (e.g. [2]) and neural network models (e.g. [3], [4], [5]) and introduction): general discussions on quantum learning [6], [7], research in 0 if wj xj threshold quantum machine learning [8], [9], [10] and quantum big output = j ≤ (1) 1 if P wj xj > threshold data analysis (e.g. [11], [12]) gained momentum in recent j years. Various quantum learning algorithms and subroutines Nonlinear activation functions suchP as hyperbolic and sigmoid are proposed(see the review articles [8], [9], [10] and the functions are more commonly used to make the the output survey [13] on general quantum learning theory): While many of a neuron smoother: i.e. a small change in any weight of the recent algorithms are based on variational quantum causes a small change in the output. It has been also argued circuits[14], [15], [16], [17], [18], some of them employs that periodic activation functions may improve the general quantum algorithms: For instance, Ref.[19] uses Grover search performance of neural nets in certain applications [25], [26], algorithm [20] to extract solution from the state which is [27]. prepared by directly mapping weights and inputs to the qubits. Here, let us first assume that an input parameter xj is The measurement in the output of a layer is used to decide expected to be seen with k number of different weights the inputs to hidden layers. In addition, Ref.[21] has used the wj1,...,wjk in the network. For each input, we will { } construct the following operator to represent the input behavior Here, αj describes the phase value of the jth eigenvalue of of a parameter xj : . After the second Hadamard gate, the final state reads the U iw 1 x following: e j j iwj2xj e N N Uxj = . (2) 1 iαj iαj .. 0 1+ e j + 1 1 e j . (7) 2√N | i | i | i − | i eiwjk xj Xj Xj Since Uxj is a k dimensional matrix, for each input xj , we If we measure the first qubit, the probability of seeing 0 and | i employ log2 k number of qubits. Therefore, n-input parame- 1 , respectively P0 and P1, can be obtained from the above | i ters lead to n number of Uxj and require n log2 k number of equation as: qubits in total: This is depicted by the following circuit: N / Ux1 / 1 iαj 2 1 P0 = 1+ e = (1 + cos(αj )) , (8) 4N | | 2N / Ux2 / Xj Xj N . 1 1 . iαj 2 P1 = 1 e = (1 cos(αj )) . (9) / Uxn / 4N | − | 2N − Xj Xj We can also describe the above circuit by the following tensor (10) product: (ω, x)= Ux2 Ux2 Ux . (3) If a threshold function is applied to the output, then U ⊗ ⊗···⊗ n In matrix form, this is equal to: 0 if P1 P0 n z = (11) i w 1 x ≤ e Pj j j 1 if P1 > P0 i P wj1xj +wn2xn e j Here, applying the measurement a few times, we can also . (4) .. obtain enough statistics for P0 and P1; and therefore describe i P wjk xj z as the success probability of the desired output: i.e., z = P . e j d The whole circuit can be also represented as an equivalent The diagonal elements of the above matrix describe an in- neural net shown in Fig.2. In the figure, f is the activation put with different weight-parameter combinations. Here, each function described by: combination is able to describe a path (or a neuron in the hidden layer) we may have in a neural net. The proposed f(α)=1 cos(α). (12) network with 1-output and n-inputs is constructed by plugging − this matrix into the circuit drawn in Fig.1. ω11 ✌ 0 H H ✌✌ z f(Σ) | i • x1 ωN12 ψ / (ω, x) / f(Σ) | i U z ωN21 Σ Fig. 1: The proposed quantum neural network with 1-output x2 f(Σ) and n-input parameters. ωN22 f(Σ) In the circuit, initializing ψ as an equal superposition state N allows the system qubits to equally| i impact the first qubit which Fig. 2: The equivalent representation of the quantum neural yields the output. In order to understand how this might work net for two input parameters and two weights for each input: as a neural net, we will go through the circuit step by step: i.e. n =2 and k =2. At the beginning, the initial input to the circuit is defined by: N 1 0 ψ = 0 j , (5) A. The Cost Function | i | i √N | i | i Xj We will use the following to describe the cost of the network where N = kn describing the matrix dimension and j is the for one sample: th vector in the standard basis. After applying the Hadamard| i j s gate and the controlled U(ω, x) to the first qubit, the state 1 2 C = (dj zj) , (13) becomes 2s − Xj N N 1 0 j + 1 eiαj j . (6) where dj is the desired output for the jth sample and s is the √ | i | i | i | i 2N Xi Xj size of the training dataset. 2 B. Backpropagation with Gradient Descent IV. DISCUSSION The update rule for the weights is described by the follow- A. Adding Biases ing: Biases can be added to a few different places in Fig.1. As an ∂C ωi = ωi η . (14) example, for input xj , we can apply a gate Ubj with diagonal − ∂wi phases representing biases to Uxj . One can also add a bias Here, the partial derivative can be found via chain rule: For gate to the output qubit before the measurement. instance, from Fig.2 with an input x1, x2 , we can obtain { } B. Generalization to Multiple Output the gradient for the weight ω11 as (the constant coefficients omitted): Different means may be considered to generalize the net- work for multiple outputs. As shown in Fig.3, one can gener- ∂Cj ∂Cj ∂zj ∂α 2 = (dj zj)P x1. (15) alize the network by sequential applications of j s. Here, a j dj U U ∂ω11 ∂zj ∂α ∂ω11 ≈ − represents a generalized multi-qubit phase gate controlled by II.
Load more

Recommended publications
  • Simulating Quantum Field Theory with a Quantum Computer
    Simulating quantum field theory with a quantum computer John Preskill Lattice 2018 28 July 2018 This talk has two parts (1) Near-term prospects for quantum computing. (2) Opportunities in quantum simulation of quantum field theory. Exascale digital computers will advance our knowledge of QCD, but some challenges will remain, especially concerning real-time evolution and properties of nuclear matter and quark-gluon plasma at nonzero temperature and chemical potential. Digital computers may never be able to address these (and other) problems; quantum computers will solve them eventually, though I’m not sure when. The physics payoff may still be far away, but today’s research can hasten the arrival of a new era in which quantum simulation fuels progress in fundamental physics. Frontiers of Physics short distance long distance complexity Higgs boson Large scale structure “More is different” Neutrino masses Cosmic microwave Many-body entanglement background Supersymmetry Phases of quantum Dark matter matter Quantum gravity Dark energy Quantum computing String theory Gravitational waves Quantum spacetime particle collision molecular chemistry entangled electrons A quantum computer can simulate efficiently any physical process that occurs in Nature. (Maybe. We don’t actually know for sure.) superconductor black hole early universe Two fundamental ideas (1) Quantum complexity Why we think quantum computing is powerful. (2) Quantum error correction Why we think quantum computing is scalable. A complete description of a typical quantum state of just 300 qubits requires more bits than the number of atoms in the visible universe. Why we think quantum computing is powerful We know examples of problems that can be solved efficiently by a quantum computer, where we believe the problems are hard for classical computers.
    [Show full text]
  • Quantum Machine Learning: Benefits and Practical Examples
    Quantum Machine Learning: Benefits and Practical Examples Frank Phillipson1[0000-0003-4580-7521] 1 TNO, Anna van Buerenplein 1, 2595 DA Den Haag, The Netherlands [email protected] Abstract. A quantum computer that is useful in practice, is expected to be devel- oped in the next few years. An important application is expected to be machine learning, where benefits are expected on run time, capacity and learning effi- ciency. In this paper, these benefits are presented and for each benefit an example application is presented. A quantum hybrid Helmholtz machine use quantum sampling to improve run time, a quantum Hopfield neural network shows an im- proved capacity and a variational quantum circuit based neural network is ex- pected to deliver a higher learning efficiency. Keywords: Quantum Machine Learning, Quantum Computing, Near Future Quantum Applications. 1 Introduction Quantum computers make use of quantum-mechanical phenomena, such as superposi- tion and entanglement, to perform operations on data [1]. Where classical computers require the data to be encoded into binary digits (bits), each of which is always in one of two definite states (0 or 1), quantum computation uses quantum bits, which can be in superpositions of states. These computers would theoretically be able to solve certain problems much more quickly than any classical computer that use even the best cur- rently known algorithms. Examples are integer factorization using Shor's algorithm or the simulation of quantum many-body systems. This benefit is also called ‘quantum supremacy’ [2], which only recently has been claimed for the first time [3]. There are two different quantum computing paradigms.
    [Show full text]
  • COVID-19 Detection on IBM Quantum Computer with Classical-Quantum Transfer Learning
    medRxiv preprint doi: https://doi.org/10.1101/2020.11.07.20227306; this version posted November 10, 2020. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY-NC-ND 4.0 International license . Turk J Elec Eng & Comp Sci () : { © TUB¨ ITAK_ doi:10.3906/elk- COVID-19 detection on IBM quantum computer with classical-quantum transfer learning Erdi ACAR1*, Ihsan_ YILMAZ2 1Department of Computer Engineering, Institute of Science, C¸anakkale Onsekiz Mart University, C¸anakkale, Turkey 2Department of Computer Engineering, Faculty of Engineering, C¸anakkale Onsekiz Mart University, C¸anakkale, Turkey Received: .201 Accepted/Published Online: .201 Final Version: ..201 Abstract: Diagnose the infected patient as soon as possible in the coronavirus 2019 (COVID-19) outbreak which is declared as a pandemic by the world health organization (WHO) is extremely important. Experts recommend CT imaging as a diagnostic tool because of the weak points of the nucleic acid amplification test (NAAT). In this study, the detection of COVID-19 from CT images, which give the most accurate response in a short time, was investigated in the classical computer and firstly in quantum computers. Using the quantum transfer learning method, we experimentally perform COVID-19 detection in different quantum real processors (IBMQx2, IBMQ-London and IBMQ-Rome) of IBM, as well as in different simulators (Pennylane, Qiskit-Aer and Cirq). By using a small number of data sets such as 126 COVID-19 and 100 Normal CT images, we obtained a positive or negative classification of COVID-19 with 90% success in classical computers, while we achieved a high success rate of 94-100% in quantum computers.
    [Show full text]
  • Quantum Inductive Learning and Quantum Logic Synthesis
    Portland State University PDXScholar Dissertations and Theses Dissertations and Theses 2009 Quantum Inductive Learning and Quantum Logic Synthesis Martin Lukac Portland State University Follow this and additional works at: https://pdxscholar.library.pdx.edu/open_access_etds Part of the Electrical and Computer Engineering Commons Let us know how access to this document benefits ou.y Recommended Citation Lukac, Martin, "Quantum Inductive Learning and Quantum Logic Synthesis" (2009). Dissertations and Theses. Paper 2319. https://doi.org/10.15760/etd.2316 This Dissertation is brought to you for free and open access. It has been accepted for inclusion in Dissertations and Theses by an authorized administrator of PDXScholar. For more information, please contact [email protected]. QUANTUM INDUCTIVE LEARNING AND QUANTUM LOGIC SYNTHESIS by MARTIN LUKAC A dissertation submitted in partial fulfillment of the requirements for the degree of DOCTOR OF PHILOSOPHY in ELECTRICAL AND COMPUTER ENGINEERING. Portland State University 2009 DISSERTATION APPROVAL The abstract and dissertation of Martin Lukac for the Doctor of Philosophy in Electrical and Computer Engineering were presented January 9, 2009, and accepted by the dissertation committee and the doctoral program. COMMITTEE APPROVALS: Irek Perkowski, Chair GarrisoH-Xireenwood -George ^Lendaris 5artM ?teven Bleiler Representative of the Office of Graduate Studies DOCTORAL PROGRAM APPROVAL: Malgorza /ska-Jeske7~Director Electrical Computer Engineering Ph.D. Program ABSTRACT An abstract of the dissertation of Martin Lukac for the Doctor of Philosophy in Electrical and Computer Engineering presented January 9, 2009. Title: Quantum Inductive Learning and Quantum Logic Synhesis Since Quantum Computer is almost realizable on large scale and Quantum Technology is one of the main solutions to the Moore Limit, Quantum Logic Synthesis (QLS) has become a required theory and tool for designing Quantum Logic Circuits.
    [Show full text]
  • Nearest Centroid Classification on a Trapped Ion Quantum Computer
    www.nature.com/npjqi ARTICLE OPEN Nearest centroid classification on a trapped ion quantum computer ✉ Sonika Johri1 , Shantanu Debnath1, Avinash Mocherla2,3,4, Alexandros SINGK2,3,5, Anupam Prakash2,3, Jungsang Kim1 and Iordanis Kerenidis2,3,6 Quantum machine learning has seen considerable theoretical and practical developments in recent years and has become a promising area for finding real world applications of quantum computers. In pursuit of this goal, here we combine state-of-the-art algorithms and quantum hardware to provide an experimental demonstration of a quantum machine learning application with provable guarantees for its performance and efficiency. In particular, we design a quantum Nearest Centroid classifier, using techniques for efficiently loading classical data into quantum states and performing distance estimations, and experimentally demonstrate it on a 11-qubit trapped-ion quantum machine, matching the accuracy of classical nearest centroid classifiers for the MNIST handwritten digits dataset and achieving up to 100% accuracy for 8-dimensional synthetic data. npj Quantum Information (2021) 7:122 ; https://doi.org/10.1038/s41534-021-00456-5 INTRODUCTION Thus, one might hope that noisy quantum computers are 1234567890():,; Quantum technologies promise to revolutionize the future of inherently better suited for machine learning computations than information and communication, in the form of quantum for other types of problems that need precise computations like computing devices able to communicate and process massive factoring or search problems. amounts of data both efficiently and securely using quantum However, there are significant challenges to be overcome to resources. Tremendous progress is continuously being made both make QML practical.
    [Show full text]
  • Explorations in Quantum Neural Networks with Intermediate Measurements
    ESANN 2020 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Online event, 2-4 October 2020, i6doc.com publ., ISBN 978-2-87587-074-2. Available from http://www.i6doc.com/en/. Explorations in Quantum Neural Networks with Intermediate Measurements Lukas Franken and Bogdan Georgiev ∗Fraunhofer IAIS - Research Center for ML and ML2R Schloss Birlinghoven - 53757 Sankt Augustin Abstract. In this short note we explore a few quantum circuits with the particular goal of basic image recognition. The models we study are inspired by recent progress in Quantum Convolution Neural Networks (QCNN) [12]. We present a few experimental results, where we attempt to learn basic image patterns motivated by scaling down the MNIST dataset. 1 Introduction The recent demonstration of Quantum Supremacy [1] heralds the advent of the Noisy Intermediate-Scale Quantum (NISQ) [2] technology, where signs of supe- riority of quantum over classical machines in particular tasks may be expected. However, one should keep in mind the limitations of NISQ-devices when study- ing and developing quantum-algorithmic solutions - among other things, these include limits on the number of gates and qubits. At the same time the interaction of quantum computing and machine learn- ing is growing, with a vast amount of literature and new results. To name a few applications, the well-known HHL algorithm [3], quantum phase estimation [5] and inner products speed-up techniques lead to further advances in Support Vector Machines [4] and Principal Component Analysis [6, 7]. Intensive progress and ongoing research has also been made towards quantum analogues of Neural Networks (QNN) [8, 9, 10].
    [Show full text]
  • Modeling Observers As Physical Systems Representing the World from Within: Quantum Theory As a Physical and Self-Referential Theory of Inference
    Modeling observers as physical systems representing the world from within: Quantum theory as a physical and self-referential theory of inference John Realpe-G´omez1∗ Theoretical Physics Group, School of Physics and Astronomy, The University of Manchestery, Manchester M13 9PL, United Kingdom and Instituto de Matem´aticas Aplicadas, Universidad de Cartagena, Bol´ıvar130001, Colombia (Dated: June 13, 2019) In 1929 Szilard pointed out that the physics of the observer may play a role in the analysis of experiments. The same year, Bohr pointed out that complementarity appears to arise naturally in psychology where both the objects of perception and the perceiving subject belong to `our mental content'. Here we argue that the formalism of quantum theory can be derived from two related intu- itive principles: (i) inference is a classical physical process performed by classical physical systems, observers, which are part of the experimental setup|this implies non-commutativity and imaginary- time quantum mechanics; (ii) experiments must be described from a first-person perspective|this leads to self-reference, complementarity, and a quantum dynamics that is the iterative construction of the observer's subjective state. This approach suggests a natural explanation for the origin of Planck's constant as due to the physical interactions supporting the observer's information process- ing, and sheds new light on some conceptual issues associated to the foundations of quantum theory. It also suggests that fundamental equations in physics are typically
    [Show full text]
  • Arxiv:2011.01938V2 [Quant-Ph] 10 Feb 2021 Ample and Complexity-Theoretic Argument Showing How Or Small Polynomial Speedups [8,9]
    Power of data in quantum machine learning Hsin-Yuan Huang,1, 2, 3 Michael Broughton,1 Masoud Mohseni,1 Ryan 1 1 1 1, Babbush, Sergio Boixo, Hartmut Neven, and Jarrod R. McClean ∗ 1Google Research, 340 Main Street, Venice, CA 90291, USA 2Institute for Quantum Information and Matter, Caltech, Pasadena, CA, USA 3Department of Computing and Mathematical Sciences, Caltech, Pasadena, CA, USA (Dated: February 12, 2021) The use of quantum computing for machine learning is among the most exciting prospective ap- plications of quantum technologies. However, machine learning tasks where data is provided can be considerably different than commonly studied computational tasks. In this work, we show that some problems that are classically hard to compute can be easily predicted by classical machines learning from data. Using rigorous prediction error bounds as a foundation, we develop a methodology for assessing potential quantum advantage in learning tasks. The bounds are tight asymptotically and empirically predictive for a wide range of learning models. These constructions explain numerical results showing that with the help of data, classical machine learning models can be competitive with quantum models even if they are tailored to quantum problems. We then propose a projected quantum model that provides a simple and rigorous quantum speed-up for a learning problem in the fault-tolerant regime. For near-term implementations, we demonstrate a significant prediction advantage over some classical models on engineered data sets designed to demonstrate a maximal quantum advantage in one of the largest numerical tests for gate-based quantum machine learning to date, up to 30 qubits.
    [Show full text]
  • Quantum Computing Methods for Supervised Learning Arxiv
    Quantum Computing Methods for Supervised Learning Viraj Kulkarni1, Milind Kulkarni1, Aniruddha Pant2 1 Vishwakarma University 2 DeepTek Inc June 23, 2020 Abstract The last two decades have seen an explosive growth in the theory and practice of both quantum computing and machine learning. Modern machine learning systems process huge volumes of data and demand massive computational power. As silicon semiconductor miniaturization approaches its physics limits, quantum computing is increasingly being considered to cater to these computational needs in the future. Small-scale quantum computers and quantum annealers have been built and are already being sold commercially. Quantum computers can benefit machine learning research and application across all science and engineering domains. However, owing to its roots in quantum mechanics, research in this field has so far been confined within the purview of the physics community, and most work is not easily accessible to researchers from other disciplines. In this paper, we provide a background and summarize key results of quantum computing before exploring its application to supervised machine learning problems. By eschewing results from physics that have little bearing on quantum computation, we hope to make this introduction accessible to data scientists, machine learning practitioners, and researchers from across disciplines. 1 Introduction Supervised learning is the most commonly applied form of machine learning. It works in two arXiv:2006.12025v1 [quant-ph] 22 Jun 2020 stages. During the training stage, the algorithm extracts patterns from the training dataset that contains pairs of samples and labels and converts these patterns into a mathematical representation called a model. During the inference stage, this model is used to make predictions about unseen samples.
    [Show full text]
  • Concentric Transmon Qubit Featuring Fast Tunability and an Anisotropic Magnetic Dipole Moment
    Concentric transmon qubit featuring fast tunability and an anisotropic magnetic dipole moment Cite as: Appl. Phys. Lett. 108, 032601 (2016); https://doi.org/10.1063/1.4940230 Submitted: 13 October 2015 . Accepted: 07 January 2016 . Published Online: 21 January 2016 Jochen Braumüller, Martin Sandberg, Michael R. Vissers, Andre Schneider, Steffen Schlör, Lukas Grünhaupt, Hannes Rotzinger, Michael Marthaler, Alexander Lukashenko, Amadeus Dieter, Alexey V. Ustinov, Martin Weides, and David P. Pappas ARTICLES YOU MAY BE INTERESTED IN A quantum engineer's guide to superconducting qubits Applied Physics Reviews 6, 021318 (2019); https://doi.org/10.1063/1.5089550 Planar superconducting resonators with internal quality factors above one million Applied Physics Letters 100, 113510 (2012); https://doi.org/10.1063/1.3693409 An argon ion beam milling process for native AlOx layers enabling coherent superconducting contacts Applied Physics Letters 111, 072601 (2017); https://doi.org/10.1063/1.4990491 Appl. Phys. Lett. 108, 032601 (2016); https://doi.org/10.1063/1.4940230 108, 032601 © 2016 AIP Publishing LLC. APPLIED PHYSICS LETTERS 108, 032601 (2016) Concentric transmon qubit featuring fast tunability and an anisotropic magnetic dipole moment Jochen Braumuller,€ 1,a) Martin Sandberg,2 Michael R. Vissers,2 Andre Schneider,1 Steffen Schlor,€ 1 Lukas Grunhaupt,€ 1 Hannes Rotzinger,1 Michael Marthaler,3 Alexander Lukashenko,1 Amadeus Dieter,1 Alexey V. Ustinov,1,4 Martin Weides,1,5 and David P. Pappas2 1Physikalisches Institut, Karlsruhe Institute of Technology,
    [Show full text]
  • Federated Quantum Machine Learning
    entropy Article Federated Quantum Machine Learning Samuel Yen-Chi Chen * and Shinjae Yoo Computational Science Initiative, Brookhaven National Laboratory, Upton, NY 11973, USA; [email protected] * Correspondence: [email protected] Abstract: Distributed training across several quantum computers could significantly improve the training time and if we could share the learned model, not the data, it could potentially improve the data privacy as the training would happen where the data is located. One of the potential schemes to achieve this property is the federated learning (FL), which consists of several clients or local nodes learning on their own data and a central node to aggregate the models collected from those local nodes. However, to the best of our knowledge, no work has been done in quantum machine learning (QML) in federation setting yet. In this work, we present the federated training on hybrid quantum-classical machine learning models although our framework could be generalized to pure quantum machine learning model. Specifically, we consider the quantum neural network (QNN) coupled with classical pre-trained convolutional model. Our distributed federated learning scheme demonstrated almost the same level of trained model accuracies and yet significantly faster distributed training. It demonstrates a promising future research direction for scaling and privacy aspects. Keywords: quantum machine learning; federated learning; quantum neural networks; variational quantum circuits; privacy-preserving AI Citation: Chen, S.Y.-C.; Yoo, S. 1. Introduction Federated Quantum Machine Recently, advances in machine learning (ML), in particular deep learning (DL), have Learning. Entropy 2021, 23, 460. found significant success in a wide variety of challenging tasks such as computer vi- https://doi.org/10.3390/e23040460 sion [1–3], natural language processing [4], and even playing the game of Go with a superhuman performance [5].
    [Show full text]
  • Future Directions of Quantum Information Processing a Workshop on the Emerging Science and Technology of Quantum Computation, Communication, and Measurement
    Future Directions of Quantum Information Processing A Workshop on the Emerging Science and Technology of Quantum Computation, Communication, and Measurement Seth Lloyd, Massachusetts Institute of Technology Dirk Englund, Massachusetts Institute of Technology Workshop funded by the Basic Research Office, Office of the Assistant Prepared by Kate Klemic Ph.D. and Jeremy Zeigler Secretary of Defense for Research & Engineering. This report does not Virginia Tech Applied Research Corporation necessarily reflect the policies or positions of the US Department of Defense Preface Over the past century, science and technology have brought remarkable new capabilities to all sectors of the economy; from telecommunications, energy, and electronics to medicine, transportation and defense. Technologies that were fantasy decades ago, such as the internet and mobile devices, now inform the way we live, work, and interact with our environment. Key to this technological progress is the capacity of the global basic research community to create new knowledge and to develop new insights in science, technology, and engineering. Understanding the trajectories of this fundamental research, within the context of global challenges, empowers stakeholders to identify and seize potential opportunities. The Future Directions Workshop series, sponsored by the Basic Research Office of the Office of the Assistant Secretary of Defense for Research and Engineering, seeks to examine emerging research and engineering areas that are most likely to transform future technology capabilities. These workshops gather distinguished academic and industry researchers from the world’s top research institutions to engage in an interactive dialogue about the promises and challenges of these emerging basic research areas and how they could impact future capabilities.
    [Show full text]