Implementing perceptron models with qubits
arXiv:1905.06728 · doi:10.1103/PhysRevA.100.020301
Abstract
We propose a method for learning a quantum probabilistic model of a perceptron. By considering a cross entropy between two density matrices we can learn a model that takes noisy output labels into account while learning. A multitude of proposals already exist that aim to utilize the curious properties of quantum systems to build a quantum perceptron, but these proposals rely on a classical cost function for the optimization procedure. We demonstrate the usage of a quantum equivalent of the classical log-likelihood, which allows for a quantum model and training procedure. We show that this allows us to better capture noisyness in data compared to a classical perceptron. By considering entangled qubits we can learn nonlinear separation boundaries, such as XOR.
References in corpus (6)
- Quantum algorithm for solving linear systems of equations
- The quest for a Quantum Neural Network
- Simulating a perceptron on a quantum computer
- Training a Binary Classifier with the Quantum Adiabatic Algorithm
- Quantum algorithm and quantum circuit for A-Optimal Projection: dimensionality reduction
- A Bayesian Probability Calculus for Density Matrices