Title | ||
---|---|---|
Learning architectures based on quantum entanglement: a simple matrix product state algorithm for image recognition. |
Abstract | ||
---|---|---|
It is a fundamental, but still elusive question whether methods based on quantum mechanics, in particular on quantum entanglement, can be used for classical information processing and machine learning. Even partial answer to this question would bring important insights to both fields of machine learning and quantum mechanics. In this work, we implement simple numerical experiments, related to pattern/images classification, in which we represent the classifiers by many-qubit quantum states written in the matrix product states (MPS). Classical machine learning algorithm is applied to these quantum states to learn the classical data. We explicitly show how quantum features (i.e., single-site and bipartite entanglement) can emerge in such represented images. Particularly, entanglement characterizes here the importance of data, and such information are used to guide the architecture of MPS, and improve the efficiency. The number of needed qubits can be reduced to less than $1/10$ of the original number. We expect such numerical experiments could open new paths in classical machine learning algorithms, and at the same time shed lights on generic quantum simulations/computations for machine learning tasks. |
Year | Venue | Field |
---|---|---|
2018 | arXiv: Machine Learning | Matrix mechanics,Quantum,Quantum entanglement,Computer science,Matrix product state,Bipartite graph,Unitary matrix,Algorithm,Quantum state,Computation |
DocType | Volume | Citations |
Journal | abs/1803.09111 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuhan Liu | 1 | 41 | 9.47 |
Xiao Zhang | 2 | 19 | 14.00 |
Maciej Lewenstein | 3 | 4 | 4.16 |
Shi-Ju Ran | 4 | 4 | 0.82 |