Zobrazeno 1 - 10
of 133
pro vyhledávání: '"Furtlehner, Cyril"'
Thanks to their simple architecture, Restricted Boltzmann Machines (RBMs) are powerful tools for modeling complex systems and extracting interpretable insights from data. However, training RBMs, as other energy-based models, on highly structured data
Externí odkaz:
http://arxiv.org/abs/2405.15376
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
Autor:
Furtlehner, Cyril
Regression models usually tend to recover a noisy signal in the form of a combination of regressors, also called features in machine learning, themselves being the result of a learning process.The alignment of the prior covariance feature matrix with
Externí odkaz:
http://arxiv.org/abs/2210.10702
Publikováno v:
SciPost Phys. 14, 032 (2023)
Restricted Boltzmann Machines are simple and powerful generative models that can encode any complex dataset. Despite all their advantages, in practice the trainings are often unstable and it is difficult to assess their quality because the dynamics a
Externí odkaz:
http://arxiv.org/abs/2206.01310
Publikováno v:
NeurIps 2021
Training Restricted Boltzmann Machines (RBMs) has been challenging for a long time due to the difficulty of computing precisely the log-likelihood gradient. Over the past decades, many works have proposed more or less successful training recipes but
Externí odkaz:
http://arxiv.org/abs/2105.13889
Autor:
Decelle, Aurélien, Furtlehner, Cyril
Publikováno v:
Phys. Rev. Lett. 127, 158303 (2021)
The restricted Boltzmann machine is a basic machine learning tool able, in principle, to model the distribution of some arbitrary dataset. Its standard training procedure appears however delicate and obscure in many respects. We bring some new insigh
Externí odkaz:
http://arxiv.org/abs/2103.10755
Autor:
Decelle, Aurélien, Furtlehner, Cyril
Publikováno v:
Chinese Physics B, Volume 30, Number 4 (2021)
This review deals with Restricted Boltzmann Machine (RBM) under the light of statistical physics. The RBM is a classical family of Machine learning (ML) models which played a central role in the development of deep learning. Viewing it as a Spin Glas
Externí odkaz:
http://arxiv.org/abs/2011.11307
In a standard multi-output classification scenario, both features and labels of training data are partially observed. This challenging issue is widely witnessed due to sensor or database failures, crowd-sourcing and noisy communication channels in in
Externí odkaz:
http://arxiv.org/abs/1912.09382
Autor:
Decelle, Aurélien, Furtlehner, Cyril
Publikováno v:
Journal of Physics A: Mathematical and Theoretical, Volume 53, Number 18 (2020)
We consider a special type of Restricted Boltzmann machine (RBM), namely a Gaussian-spherical RBM where the visible units have Gaussian priors while the vector of hidden variables is constrained to stay on an ${\mathbbm L}_2$ sphere. The spherical co
Externí odkaz:
http://arxiv.org/abs/1910.14544
Publikováno v:
Decelle, A., Fissore, G. & Furtlehner, C. J Stat Phys (2018)
We investigate the thermodynamic properties of a Restricted Boltzmann Machine (RBM), a simple energy-based generative model used in the context of unsupervised learning. Assuming the information content of this model to be mainly reflected by the spe
Externí odkaz:
http://arxiv.org/abs/1803.01960