
Matrix Product State Based Quantum Classifier
In recent years, interest in expressing the success of neural networks t...
read it

Hybrid quantumclassical classifier based on tensor network and variational quantum circuit
One key step in performing quantum machine learning (QML) on noisy inter...
read it

Fock Stateenhanced Expressivity of Quantum Machine Learning Models
The dataembedding process is one of the bottlenecks of quantum machine ...
read it

Generalization in Quantum Machine Learning: a Quantum Information Perspective
We study the machine learning problem of generalization when quantum ope...
read it

Representation of binary classification trees with binary features by quantum circuits
We propose a quantum representation of binary classification trees with ...
read it

Negational Symmetry of Quantum Neural Networks for Binary Pattern Classification
Entanglement is a physical phenomenon, which has fueled recent successes...
read it

A simple approach to design quantum neural networks and its applications to kernellearning methods
We give an explicit simple method to build quantum neural networks (QNNs...
read it
Quantum Discriminator for Binary Classification
Quantum computers operate in the highdimensional tensor product spaces and are known to outperform classical computers on many problems. They are poised to accelerate machine learning tasks in the future. In this work, we operate in the quantum machine learning (QML) regime where a QML model is trained using a quantumclassical hybrid algorithm and inferencing is performed using a quantum algorithm. We leverage the traditional twostep machine learning workflow, where features are extracted from the data in the first step and a discriminator acting on the extracted features is used to classify the data in the second step. Assuming that the binary features have been extracted from the data, we propose a quantum discriminator for binary classification. The quantum discriminator takes as input the binary features of a data point and a prediction qubit in the zero state, and outputs the correct class of the data point. The quantum discriminator is defined by a parameterized unitary matrix U_Θ containing 𝒪(N) parameters, where N is the number of data points in the training data set. Furthermore, we show that the quantum discriminator can be trained in 𝒪(N log N) time using 𝒪(N log N) classical bits and 𝒪(log N) qubits. We also show that inferencing for the quantum discriminator can be done in 𝒪(N) time using 𝒪(log N) qubits. Finally, we use the quantum discriminator to classify the XOR problem on the IBM Q universal quantum computer with 100% accuracy.
READ FULL TEXT
Comments
There are no comments yet.