English
Related papers

Related papers: Analogy between Boltzmann machines and Feynman pat…

200 papers

Boltzmann machines are undirected graphical models with two-state stochastic variables, in which the logarithms of the clique potentials are quadratic functions of the node states. They have been widely studied in the neural computing…

Machine Learning · Computer Science 2013-02-01 Neil D. Lawrence , Christopher M. Bishop , Michael I. Jordan

The Feynman path integral has revolutionized modern approaches to quantum physics. Although the path integral formalism has proven very successful and spawned several approximation schemes, the direct evaluation of real-time path integrals…

Quantum Physics · Physics 2025-01-28 Job Feldbrugge , Joshua Y. L. Jones

Machine learning models can inherit hidden behavioral traits through innocuous public interfaces, a phenomenon known as subliminal learning. Here we extend this framework to quantum models and study two distillation pathways: an auxiliary…

Quantum Physics · Physics 2026-05-29 Shi-Xin Zhang , Yu-Qin Chen

We motivate an intuitive way to think about quantum circuit optimization problem inspired by Feynman's path formalism. While the use of path integrals in quantum circuits remains largely underdeveloped due to the lack of definition of the…

Quantum Physics · Physics 2024-11-15 Kartik Anand

Deep Boltzmann machines (DBMs), one of the first ``deep'' learning methods ever studied, are multi-layered probabilistic models governed by a pairwise energy function that describes the likelihood of all variables/nodes in the network. In…

Machine Learning · Computer Science 2023-07-12 Zhili Feng , Ezra Winston , J. Zico Kolter

Quantum machine learning models based on parametrized quantum circuits, also called quantum neural networks (QNNs), are considered to be among the most promising candidates for applications on near-term quantum devices. Here we explore the…

Quantum Physics · Physics 2024-07-08 Chris Mingard , Jessica Pointing , Charles London , Yoonsoo Nam , Ard A. Louis

The Quantum Lattice Boltzmann Method (QLBM) has emerged as one of the most promising quantum computing approaches for the numerical simulation of problems in computational fluid dynamics (CFD). The dynamics is formulated in terms of…

It is apparent to anyone who thinks about it that, to a large degree, the basic concepts of Newtonian physics are quite intuitive, but quantum mechanics is not. My purpose in this talk is to introduce you to a new, much more intuitive way…

Quantum Physics · Physics 2009-02-12 Marvin Weinstein

The promise of quantum neural nets, which utilize quantum effects to model complex data sets, has made their development an aspirational goal for quantum machine learning and quantum computing in general. Here we provide new methods of…

Quantum Physics · Physics 2017-12-27 Maria Kieferova , Nathan Wiebe

Artificial Intelligence (AI) systems have shown good success at classifying. However, the lack of explainability is a true and significant challenge, especially in high-stakes domains, such as health and finance, where understanding is…

Machine Learning · Computer Science 2026-01-14 A. M. A. S. D. Alagiyawanna , Asoka Karunananda , Thushari Silva , A. Mahasinghe

A restricted Boltzmann machine (RBM) is an undirected graphical model constructed for discrete or continuous random variables, with two layers, one hidden and one visible, and no conditional dependency within a layer. In recent years, RBMs…

Machine Learning · Statistics 2019-09-12 Andee Kaplan , Daniel Nordman , Stephen Vardeman

In this paper we show how Feynman diagrams, which are used as a tool to implement perturbation theory in quantum field theory, can be very useful also in classical mechanics, provided we introduce also at the classical level concepts like…

High Energy Physics - Theory · Physics 2009-11-11 R. Penco , D. Mauro

We study certain aspects of the effective, occasionally called collective, description of complex quantum systems within the framework of the path integral formalism, in which the environment is integrated out. Generalising the standard…

Statistical Mechanics · Physics 2007-05-23 U. Eckern , M. J. Gruber , P. Schwab

It is discussed an opportunity to introduce new class of quantum algorithms based on possibility to express amplitude of transition between two states of quantum system as sum of some function along all possible classical paths. Continuous…

Quantum Physics · Physics 2007-05-23 Alexander Yu. Vlasov

This model is one of the possible geometrical interpretations of Quantum Mechanics where found to every image Path correspondence the geodesic trajectory of classical test particles in the random geometry of the stochastic fields…

Quantum Physics · Physics 2008-05-28 Timur F. Kamalov

Compared to classical optical coherence theory based on Maxwell's electromagnetic theory and Glauber's quantum optical coherence theory based on matrix mechanics formulation of quantum mechanics, quantum optical coherence theory based on…

Quantum Physics · Physics 2024-09-18 Jianbin Liu , Yu Zhou , Hui Chen , Huaibin Zheng , Yuchen He , Fuli Li , Zhuo Xu

Restricted Boltzmann machines (RBM) and deep Boltzmann machines (DBM) are important models in machine learning, and recently found numerous applications in quantum many-body physics. We show that there are fundamental connections between…

Statistical Mechanics · Physics 2021-09-01 Sujie Li , Feng Pan , Pengfei Zhou , Pan Zhang

We discuss probabilistic neural networks with a fixed internal representation as models for machine understanding. Here understanding is intended as mapping data to an already existing representation which encodes an {\em a priori}…

Disordered Systems and Neural Networks · Physics 2023-12-07 Rongrong Xie , Matteo Marsili

Given an arbitrary Lagrangian function on \RR^d and a choice of classical path, one can try to define Feynman's path integral supported near the classical path as a formal power series parameterized by "Feynman diagrams," although these…

Mathematical Physics · Physics 2019-11-05 Theo Johnson-Freyd

These lectures are intended for graduate students who want to acquire a working knowledge of path integral methods in a wide variety of fields in physics. In general the presentation is elementary and path integrals are developed in the…

Nuclear Theory · Physics 2017-08-01 R. Rosenfelder