Training Hybrid Classical-Quantum Classifiers via Stochastic Variational Optimization
arXiv:2201.08629 · doi:10.1109/LSP.2022.3164852
Abstract
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 qubits per neuron. To facilitate implementation of the QGLMs, all weights and activations are binary. While the state of the art on training strategies for this class of models is limited to exhaustive search and single-neuron perceptron-like bit-flip strategies, this letter introduces a stochastic variational optimization approach that enables the joint training of quantum and classical layers via stochastic gradient descent. Experiments show the advantages of the approach for a variety of activation functions implemented by QGLM neurons.
arXiv commentsubmitted for publication
References in corpus (16)
- Quantum Computing in the NISQ era and beyond
- Quantum Machine Learning
- Variational Quantum Algorithms
- Supervised learning with quantum enhanced feature spaces
- Noisy intermediate-scale quantum (NISQ) algorithms
- Kernel methods in machine learning
- Quantum Convolutional Neural Networks
- Transfer learning in hybrid classical-quantum neural networks
- A generative modeling approach for benchmarking and training shallow quantum circuits
- Quantum Boltzmann Machine
- An Artificial Neuron Implemented on an Actual Quantum Processor
- Implementing a distance-based classifier with a quantum interference circuit
- Quantum computing models for artificial neural networks
- Quantum assisted Gaussian process regression
- Quantum implementation of an artificial feed-forward neural network
- Improved Boltzmann machines with error corrected quantum annealing