Supervised learning with quantum-enhanced feature spaces
| Autor: | Vojtěch Havlíček, Antonio D. Córcoles, Kristan Temme, Aram W. Harrow, Abhinav Kandala, Jerry M. Chow, Jay M. Gambetta |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Quantum machine learning Computer science Computation Feature vector FOS: Physical sciences Machine Learning (stat.ML) Quantum entanglement 01 natural sciences 010305 fluids & plasmas Quantum circuit symbols.namesake Statistics - Machine Learning Quantum state 0103 physical sciences 010306 general physics Quantum Quantum computer Quantum Physics Multidisciplinary Training set Supervised learning Hilbert space Estimator Support vector machine Kernel method ComputerSystemsOrganization_MISCELLANEOUS Kernel (statistics) symbols Quantum algorithm Quantum Physics (quant-ph) Algorithm |
| Zdroj: | arXiv |
| ISSN: | 1476-4687 0028-0836 |
| DOI: | 10.1038/s41586-019-0980-2 |
| Popis: | Machine learning and quantum computing are two technologies each with the potential for altering how computation is performed to address previously untenable problems. Kernel methods for machine learning are ubiquitous for pattern recognition, with support vector machines (SVMs) being the most well-known method for classification problems. However, there are limitations to the successful solution to such problems when the feature space becomes large, and the kernel functions become computationally expensive to estimate. A core element to computational speed-ups afforded by quantum algorithms is the exploitation of an exponentially large quantum state space through controllable entanglement and interference. Here, we propose and experimentally implement two novel methods on a superconducting processor. Both methods represent the feature space of a classification problem by a quantum state, taking advantage of the large dimensionality of quantum Hilbert space to obtain an enhanced solution. One method, the quantum variational classifier builds on [1,2] and operates through using a variational quantum circuit to classify a training set in direct analogy to conventional SVMs. In the second, a quantum kernel estimator, we estimate the kernel function and optimize the classifier directly. The two methods present a new class of tools for exploring the applications of noisy intermediate scale quantum computers [3] to machine learning. Fixed typos, added figures and discussion about quantum error mitigation |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink