University of Western Australia(西澳大学);CSIRO’s Data61(澳大利亚联邦科学与工业研究组织Data61)
Larry Huynh, Jin Hong, Ajmal Mian, Hajime Suzuki, Yanqiu Wu, Seyit Camtepe
备注:
59 pages, 13 figures, 9 tables. - Edited for spelling, grammar, and corrected minor typos in formulas - Adjusted wording in places for better clarity - Corrected contact info - Added Table 1 to clarify variables used in dequantized algs. - Added subsections in QVAS discussing QCBMs and TN-based VQC models - Included additional references as requested by authors to ensure a more exhaustive survey
Quantum-inspired Machine Learning (QiML) is a burgeoning field, receiving global attention from researchers for its potential to leverage principles of quantum mechanics within classical computational frameworks. However, current review literature often presents a superficial exploration of QiML, focusing instead on the broader Quantum Machine Learning (QML) field. In response to this gap, this survey provides an integrated and comprehensive examination of QiML, exploring QiML's diverse research domains including tensor network simulations, dequantized algorithms, and others, showcasing recent advancements, practical applications, and illuminating potential future research avenues. Further, a concrete definition of QiML is established by analyzing various prior interpretations of the term and their inherent ambiguities. As QiML continues to evolve, we anticipate a wealth of future developments drawing from quantum mechanics, quantum computing, and classical machine learning, enriching the field further. This survey serves as a guide for researchers and practitioners alike, providing a holistic understanding of QiML's current landscape and future directions.
Quantum-inspired annealers as Boltzmann generators for machine learning and statistical physics
Russian Quantum Center(俄罗斯量子中心);Moscow Institute of Physics and Technology(莫斯科物理技术学院);University of Oxford(牛津大学);P. N. Lebedev Physics Institute(P. N. 列别杰夫物理研究所)
Variational decision diagrams for quantum-inspired machine learning applications
D-Wave Systems(D-Wave系统);Zapata Computing Inc.(Zapata计算公司);Grupo de Superconductividad y Nanotecnología, Departamento de Física, Universidad Nacional de Colombia(超导与纳米技术小组,物理系,哥伦比亚国家大学)
Quantum Inspired Encoding Strategies for Machine Learning Models: Proposing and Evaluating Instance Level, Global Discrete, and Class Conditional Representations
University of Science and Technology of China(中国科学技术大学);CAS Centre for Excellence and Synergetic Innovation Centre in Quantum Information and Quantum Physics(中国科学院量子信息与量子科技创新卓越中心);University of Oxford(牛津大学);Hefei National Laboratory for Physical Sciences at Microscale(合肥微尺度物质科学国家实验室)
Quantum-inspired tensor networks in machine learning models
Vicomtech Foundation, Basque Research and Technology Alliance (BRTA)(维科姆科技基金会,巴斯克研究与技术联盟(BRTA));University of Deusto(德乌斯大学);Escuela Técnica Superior de Ingeniería de Sistemas Informáticos, Universidad Politécnica de Madrid(马德里理工大学信息系统工程学院);Department of Applied Physics, University of Geneva(日内瓦大学应用物理系)
Leveraging dendritic properties to advance machine learning and neuro-inspired computing
Institute of Molecular Biology and Biotechnology (IMBB), Foundation for Research and Technology Hellas (FORTH)(希腊研究与技术基金会分子生物学与生物技术研究所);University of Crete(克里特大学)
Quantum-inspired Machine Learning on high-energy physics data
Tensor Solutions(张量解决方案公司);Institute for Complex Quantum Systems, University of Ulm(乌尔姆大学复杂量子系统研究所);Università di Padova(帕多瓦大学);INFN(意大利国家核物理研究所);Universität des Saarlandes(萨尔大学);Padua Quantum Technologies Research Center, Università degli Studi di Padova(帕多瓦大学帕多瓦量子技术研究中心)
A Developmentally-Inspired Examination of Shape versus Texture Bias in Machines
New York University(纽约大学)
在发育的早期,儿童学会将新的类别标签扩展到具有相同形状的物体,这种现象称为形状偏见。受这些发现的启发,Geirhos et al.(2019)通过构建具有冲突形状和纹理线索的图像,研究了深度神经网络是否表现出形状或纹理偏见。他们发现,卷积神经网络强烈倾向于根据纹理而不是形状对熟悉的物体进行分类,这表明了纹理偏见。然而,在这项研究中测试网络的方式与通常测试儿童的方式之间存在许多差异。在这项工作中,我们通过调整Geirhos et al.(2019)的刺激和程序来重新审视神经网络的归纳偏差,以更紧密地遵循发展范式,并在广泛的预训练神经网络上进行测试。在三个实验中,我们发现,当在更接近复制发育过程的条件下进行测试时,深层神经网络表现出对形状而不是纹理的偏好。
Instructor-inspired Machine Learning for Robust Molecular Property Prediction
Computer Science Department, Stanford University(斯坦福大学计算机科学系);School of Computer Science and Technology, Wuhan University of Science and Technology(武汉科技大学计算机科学与技术学院);School of Engineering, Westlake University(西湖大学工程学院)
Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent
University of Rostock(罗斯托克大学);Software Competence Center Hagenberg GmbH(哈根堡软件能力中心有限公司);University of St Andrews(圣安德鲁斯大学);Primetals Technologies Austria GmbH(普锐特冶金技术奥地利有限公司);Johannes Kepler University Linz(约翰内斯·开普勒大学林茨分校)
Scientific intuition inspired by machine learning generated hypotheses
University of Toronto(多伦多大学);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Vector Institute for Artificial Intelligence(矢量人工智能研究所);National Research Council of Canada(加拿大国家研究委员会);Canadian Institute for Advanced Research (CIFAR)(加拿大高等研究院)
Geomagnetic Survey Interpolation with the Machine Learning Approach
Schmidt Institute of Physics of the Earth of the Russian Academy of Sciences(俄罗斯科学院施密特地球物理研究所);Geophysical Center of the Russian Academy of Sciences(俄罗斯科学院地球物理中心)
Machine learning for Earth System Science (ESS): A survey, status and future directions for South Asia
Indian Institute of Tropical Meteorology(印度热带气象研究所);Jackson School of Geosciences, The University of Texas at Austin(德克萨斯大学奥斯汀分校杰克逊地球科学学院);Indian Institute of Technology Bombay(印度理工学院孟买分校);Indian Institute of Science(印度科学理工学院);Borehole Geophysics Research Laboratory(钻孔地球物理研究实验室)
Quantum-Inspired Machine Learning for Molecular Docking
School of Automation Science and Engineering, South China University of Technology(华南理工大学自动化科学与工程学院);Central Research Institute, 2012 Labs, Huawei Technologies(华为技术有限公司2012实验室中央研究院);Laboratory of AI for Science, Huawei Cloud Computing Technologies Co., Ltd(华为云计算技术有限公司科学人工智能实验室);Shenzhen Institute for Quantum Science and Engineering(深圳量子科学与工程研究院)