{"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/quantum-neuron-an-elementary-building-block","title":"Quantum Neuron: an elementary building block for machine learning on quantum computers","arxiv_id":"1711.11240","date":"2017-11-30","proceeding":null,"authors":["Yudong Cao","Gian Giacomo Guerreschi","Alán Aspuru-Guzik"],"abstract":"Even the most sophisticated artificial neural networks are built by\naggregating substantially identical units called neurons. A neuron receives\nmultiple signals, internally combines them, and applies a non-linear function\nto the resulting weighted sum. Several attempts to generalize neurons to the\nquantum regime have been proposed, but all proposals collided with the\ndifficulty of implementing non-linear activation functions, which is essential\nfor classical neurons, due to the linear nature of quantum mechanics. Here we\npropose a solution to this roadblock in the form of a small quantum circuit\nthat naturally simulates neurons with threshold activation. Our quantum circuit\ndefines a building block, the \"quantum neuron\", that can reproduce a variety of\nclassical neural network constructions while maintaining the ability to process\nsuperpositions of inputs and preserve quantum coherence and entanglement. In\nthe construction of feedforward networks of quantum neurons, we provide\nnumerical evidence that the network not only can learn a function when trained\nwith superposition of inputs and the corresponding output, but that this\ntraining suffices to learn the function on all individual inputs separately.\nWhen arranged to mimic Hopfield networks, quantum neural networks exhibit\nproperties of associative memory. Patterns are encoded using the simple Hebbian\nrule for the weights and we demonstrate attractor dynamics from corrupted\ninputs. Finally, the fact that our quantum model closely captures (traditional)\nneural network dynamics implies that the vast body of literature and results on\nneural networks becomes directly relevant in the context of quantum machine\nlearning.","url_abs":"http://arxiv.org/abs/1711.11240v1","url_pdf":"http://arxiv.org/pdf/1711.11240v1.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":"quantum-neuron-an-elementary-building-block","repo_url":"https://github.com/Alekxos/Quamodo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"quantum-neuron-an-elementary-building-block","repo_url":"https://github.com/inJeans/qnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"quantum-machine-learning","task_name":"Quantum Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}