Zobrazeno 1 - 10
of 958
pro vyhledávání: '"Decelle A"'
Restricted Boltzmann Machines (RBMs) are effective tools for modeling complex systems and deriving insights from data. However, training these models with highly structured data presents significant challenges due to the slow mixing characteristics o
Externí odkaz:
http://arxiv.org/abs/2405.15376
In this paper, we investigate the feature encoding process in a prototypical energy-based generative model, the Restricted Boltzmann Machine (RBM). We start with an analytical investigation using simplified architectures and data structures, and end
Externí odkaz:
http://arxiv.org/abs/2405.14689
Cosmological simulations play a key role in the prediction and understanding of large scale structure formation from initial conditions. We make use of GAN-based Autoencoders (AEs) in an attempt to predict structure evolution within simulations. The
Externí odkaz:
http://arxiv.org/abs/2403.02171
Publikováno v:
SciPost Phys. 16, 095 (2024)
Generative models offer a direct way of modeling complex data. Energy-based models attempt to encode the statistical correlations observed in the data at the level of the Boltzmann weight associated with an energy function in the form of a neural net
Externí odkaz:
http://arxiv.org/abs/2309.02292
Publikováno v:
Phys. Rev. E 109, 065313 (2024)
We characterize the equilibrium properties of a model of $y$ coupled binary perceptrons in the teacher-student scenario, subject to a suitable cost function, with an explicit ferromagnetic coupling proportional to the Hamming distance between the stu
Externí odkaz:
http://arxiv.org/abs/2308.03743
Publikováno v:
IEEE: Transactions on Pattern Analysis and Machine Intelligence, 2024
In this study, we address the challenge of using energy-based models to produce high-quality, label-specific data in complex structured datasets, such as population genetics, RNA or protein sequences data. Traditional training methods encounter diffi
Externí odkaz:
http://arxiv.org/abs/2307.06797
Publikováno v:
Phys. Rev. E 108, 014110 (2023)
Datasets in the real world are often complex and to some degree hierarchical, with groups and sub-groups of data sharing common characteristics at different levels of abstraction. Understanding and uncovering the hidden structure of these datasets is
Externí odkaz:
http://arxiv.org/abs/2302.01851
In this paper, we quantify the impact of using non-convergent Markov chains to train Energy-Based models (EBMs). In particular, we show analytically that EBMs trained with non-persistent short runs to estimate the gradient can perfectly reproduce a s
Externí odkaz:
http://arxiv.org/abs/2301.09428
Autor:
Yang Yang, PhD, Sydne McCluskey, PhD, Mohamad Bydon, MD, Jaspal Ricky Singh, MD, Robert D. Sheeler, MD, Karim Rizwan Nathani, MBBS, Ana C. Krieger, MD, MPH, Neel D. Mehta, MD, Joshua Weaver, MD, Libin Jia, MD, Sharon DeCelle, MS, PT, LPC, Robert C. Schlagal, PhD, Jay Ayar, DrPH (c), MPH, BDS, Sahar Abduljawad, DrPH, MPH, Steven D. Stovitz, MD, MS, Ravindra Ganesh, MBBS, MD, Jay Verkuilen, PhD, Kenneth A. Knapp, PhD, Lin Yang, PhD, Roger Härtl, MD
Publikováno v:
North American Spine Society Journal, Vol 20, Iss , Pp 100557- (2024)
ABSTRACT: Background: Mind-body treatments have the potential to manage pain, yet their effectiveness when delivered online for the treatment of low back pain (LBP) is unknown. We sought to evaluate whether a virtually delivered mind-body program int
Externí odkaz:
https://doaj.org/article/4f6bd1a5d2804ca6a2b072479501a7f5
Publikováno v:
A&A 674, A150 (2023)
Degeneracies among parameters of the cosmological model are known to drastically limit the information contained in the matter distribution. In the first paper of this series, we shown that the cosmic web environments; namely the voids, walls, filame
Externí odkaz:
http://arxiv.org/abs/2212.06838