Classification with Quantum Neural Networks on Near Term Processors

@article{Farhi2018ClassificationWQ,
  title={Classification with Quantum Neural Networks on Near Term Processors},
  author={Edward Farhi and Hartmut Neven},
  journal={arXiv: Quantum Physics},
  year={2018}
}
  • E. FarhiH. Neven
  • Published 16 February 2018
  • Physics, Computer Science
  • arXiv: Quantum Physics
We introduce a quantum neural network, QNN, that can represent labeled data, classical or quantum, and be trained by supervised learning. The quantum circuit consists of a sequence of parameter dependent unitary transformations which acts on an input quantum state. For binary classification a single Pauli operator is measured on a designated readout qubit. The measured output is the quantum neural network’s predictor of the binary label of the input state. We show through classical simulation… 

Figures from this paper

Scalable Quantum Neural Networks for Classification

An approach to implementing a scalable quantum neural network (SQNN) by utilizing the quantum resource of multiple small-size quantum devices cooperatively, which shows that the SQNN model achieves a comparable classification accuracy to a regular QNN model of the same scale.

Hierarchical quantum classifiers

It is shown how quantum algorithms based on two tensor network structures can be used to classify both classical and quantum data and may enable classification of two-dimensional images and entangled quantum data more efficiently than is possible with classical methods.

Quantum activation functions for quantum neural networks

This work presents a quantum algorithm which is capable to approximate any analytic activation functions to any given order of its power series, and recast the science of artificial neural networks in the architecture of gate-model quantum computers.

Variational Learning for Quantum Artificial Neural Networks

This work presents an original realization of efficient individual quantum nodes based on variational unsampling protocols, and investigates different learning strategies involving global and local layerwise cost functions, and assess their performances also in the presence of statistical measurement noise.

Exploring quantum perceptron and quantum neural network structures with a teacher-student scheme

A teacher-student scheme that could systematically compare any QNN architectures and evaluate their relative expressive power is introduced to avoid training on arbitrary data sets and allow to compare the learning capacity of different models directly via the loss, the prediction map, the accuracy and the relative entropy between the prediction maps.

Realizing quantum convolutional neural networks on a superconducting quantum processor to recognize quantum phases

Quantum computing crucially relies on the ability to efficiently characterize the quantum states output by quantum hardware. Conventional methods which probe these states through direct measurements

Variational quantum unsampling on a quantum photonic processor

The variational quantum unsampling protocol is introduced, a nonlinear quantum neural network approach for verification and inference of near-term quantum circuit outputs that can variationally train a quantum operation to unravel the action of an unknown unitary on a known input state.

Universal discriminative quantum neural networks

This work shows that it is possible to train a quantum circuit to discriminate quantum data with a trade-off between minimizing error rates and inconclusiveness rates of the classification tasks and achieves a performance which is close to the theoretically optimal values and a generalization ability to previously unseen quantum data.

Training deep quantum neural networks

A noise-robust architecture for a feedforward quantum neural network, with qudits as neurons and arbitrary unitary operations as perceptrons, whose training procedure is efficient in the number of layers.

Barren plateaus in quantum neural network training landscapes

It is shown that for a wide class of reasonable parameterized quantum circuits, the probability that the gradient along any reasonable direction is non-zero to some fixed precision is exponentially small as a function of the number of qubits.
...

References

SHOWING 1-10 OF 25 REFERENCES

Quantum generalisation of feedforward neural networks

It is demonstrated numerically that the proposed quantum generalisation of a classical neural network can compress quantum states onto a minimal number of qubits, create a quantum autoencoder, and discover quantum communication protocols such as teleportation.

Quantum Neuron: an elementary building block for machine learning on quantum computers

A small quantum circuit is proposed that naturally simulates neurons with threshold activation and defines a building block, the "quantum neuron", that can reproduce a variety of classical neural network constructions while maintaining the ability to process superpositions of inputs and preserve quantum coherence and entanglement.

Quantum autoencoders for efficient compression of quantum data

The model of a quantum autoencoder is introduced to perform similar tasks on quantum data to compress ground states of the Hubbard model and molecular Hamiltonians and shows an example of a simple programmable circuit that can be trained as an efficient autoenCoder.

A quantum speedup in machine learning: finding an N-bit Boolean function for a classification

It is shown that quantum superposition enables quantum learning that is faster than classical learning by expanding the approximate solution regions, i.e., the acceptable regions.

Unsupervised Machine Learning on a Hybrid Quantum Computer

This paper uses the quantum approximate optimization algorithm in conjunction with a gradient-free Bayesian optimization to train the quantum machine, and finds evidence that classical optimization can be used to train around both coherent and incoherent imperfections.

Demonstration of quantum advantage in machine learning

D. Ristè and colleagues at Raytheon BBN Technologies, with collaborators at IBM, have demonstrated that a quantum advantage already appears with only a few quantum bits and a highly noisy system.

An introduction to quantum machine learning

This contribution gives a systematic overview of the emerging field of quantum machine learning and presents the approaches as well as technical details in an accessible way, and discusses the potential of a future theory of quantum learning.

Quantum Algorithms for Fixed Qubit Architectures

Gate model quantum computers with too many qubits to be simulated by available classical computers are about to arrive. We present a strategy for programming these devices without error correction or

Demonstration of a small programmable quantum computer with atomic qubits

A five-qubit trapped-ion quantum computer that can be programmed in software to implement arbitrary quantum algorithms by executing any sequence of universal quantum logic gates, which provides the flexibility to implement a variety of algorithms without altering the hardware.

Demonstration of a quantum error detection code using a square lattice of four superconducting qubits

This work presents a quantum error detection protocol on a two-by-two planar lattice of superconducting qubits that detects an arbitrary quantum error on an encoded two-qubit entangled state via quantum non-demolition parity measurements on another pair of error syndrome qubits.