{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/entanglement-guided-architectures-of-machine","title":"Entanglement-guided architectures of machine learning by quantum tensor network","arxiv_id":"1803.09111","date":"2018-03-24","proceeding":null,"authors":["Yuhan Liu","Xiao Zhang","Maciej Lewenstein","Shi-Ju Ran"],"abstract":"It is a fundamental, but still elusive question whether the schemes based on\nquantum mechanics, in particular on quantum entanglement, can be used for\nclassical information processing and machine learning. Even partial answer to\nthis question would bring important insights to both fields of machine learning\nand quantum mechanics. In this work, we implement simple numerical experiments,\nrelated to pattern/images classification, in which we represent the classifiers\nby many-qubit quantum states written in the matrix product states (MPS).\nClassical machine learning algorithm is applied to these quantum states to\nlearn the classical data. We explicitly show how quantum entanglement (i.e.,\nsingle-site and bipartite entanglement) can emerge in such represented images.\nEntanglement characterizes here the importance of data, and such information\nare practically used to guide the architecture of MPS, and improve the\nefficiency. The number of needed qubits can be reduced to less than 1/10 of the\noriginal number, which is within the access of the state-of-the-art quantum\ncomputers. We expect such numerical experiments could open new paths in\ncharactering classical machine learning algorithms, and at the same time shed\nlights on the generic quantum simulations/computations of machine learning\ntasks.","url_abs":"http://arxiv.org/abs/1803.09111v3","url_pdf":"http://arxiv.org/pdf/1803.09111v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"entanglement-guided-architectures-of-machine","repo_url":"https://github.com/YuhanLiuSYSU/MPS_ImageClassifier","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"GPL-2.0"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.09111","atlas_url":"https://app.syntology.ai/?focus=1803.09111","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}