Training Hybrid Classical-Quantum Classifiers via Stochastic Variational Optimization

@article{Nikoloska2022TrainingHC,
  title={Training Hybrid Classical-Quantum Classifiers via Stochastic Variational Optimization},
  author={Ivana Nikoloska and Osvaldo Simeone},
  journal={IEEE Signal Processing Letters},
  year={2022},
  volume={29},
  pages={977-981}
}
Quantum machine learning has emerged as a potential practical application of near-term quantum devices. In this work, we study a two-layer hybrid classical-quantum classifier in which a first layer of quantum stochastic neurons implementing generalized linear models (QGLMs) is followed by a second classical combining layer. The input to the first, hidden, layer is obtained via amplitude encoding in order to leverage the exponential size of the fan-in of the quantum neurons in the number of… 

Figures and Tables from this paper

Scalable Quantum Convolutional Neural Networks

This work proposes a new version of QCNN, named scalable quantum convolutional neural network (sQCNN), and proposes an sQCNN training algorithm named reverse fidelity training (RF-Train) that maximizes the performance of sQ CNN.

References

SHOWING 1-10 OF 29 REFERENCES

Transfer learning in hybrid classical-quantum neural networks

This work uses the cross-platform software library PennyLane to experimentally test a high-resolution image classifier with two different quantum computers, respectively provided by IBM and Rigetti, to propose different implementations of hybrid transfer learning.

A generative modeling approach for benchmarking and training shallow quantum circuits

A quantum circuit learning algorithm that can be used to assist the characterization of quantum devices and to train shallow circuits for generative tasks is proposed and it is demonstrated that this approach can learn an optimal preparation of the Greenberger-Horne-Zeilinger states.

A Hybrid Quantum-Classical Neural Network Architecture for Binary Classification

This work proposes a hybrid quantum-classical neural network architecture where each neuron is a variational quantum circuit and empirically analyzes the performance of this hybrid neural network on a series of binary classification data sets using a simulated universal quantum computer and a state of the art universal quantumcomputer.

Quantum convolutional neural networks

A quantum circuit-based algorithm inspired by convolutional neural networks is shown to successfully perform quantum phase recognition and devise quantum error correcting codes when applied to arbitrary input quantum states.

Quantum implementation of an artificial feed-forward neural network

It is demonstrated that this network made of quantum artificial neurons can be equivalently operated either via classical control or in a completely coherent fashion, thus opening the way to hybrid as well as fully quantum solutions for artificial intelligence to be run on near-term intermediate-scale quantum hardware.

Quantum machine learning with small-scale devices: Implementing a distance-based classifier with a quantum interference circuit

A distance-based classifier that is realised by a simple quantum interference circuit that computes the distance between data points in quantum parallel and is demonstrated using the IBM Quantum Experience and analysed with numerical simulations.

Quantum Boltzmann Machine

This work proposes a new machine learning approach based on quantum Boltzmann distribution of a transverse-field Ising Hamiltonian that allows the QBM efficiently by sampling and discusses the possibility of using quantum annealing processors like D-Wave for QBM training and application.

Limitations of error corrected quantum annealing in improving the performance of Boltzmann machines

A counterintuitive aspect of the results is that the output distribution generally becomes less Gibbs-like with increasing nesting level and increasing anneal times, which shows that improved training performance can be achieved without equilibration to the target Gibbs distribution.

Quantum assisted Gaussian process regression

It is shown that even in some cases not ideally suited to the quantum linear systems algorithm, a polynomial increase in efficiency still occurs, leading to an exponential reduction in computation time in some instances.

Quantum Computing in the NISQ era and beyond

Noisy Intermediate-Scale Quantum (NISQ) technology will be available in the near future, and the 100-qubit quantum computer will not change the world right away - but it should be regarded as a significant step toward the more powerful quantum technologies of the future.