Zobrazeno 1 - 10
of 159
pro vyhledávání: '"Florent Krzakala"'
Publikováno v:
PLoS Computational Biology, Vol 19, Iss 1, p e1010813 (2023)
The advent of comprehensive synaptic wiring diagrams of large neural circuits has created the field of connectomics and given rise to a number of open research questions. One such question is whether it is possible to reconstruct the information stor
Externí odkaz:
https://doaj.org/article/e8652efcaa314a0ea8d3305132cce8fc
Publikováno v:
Machine Learning: Science and Technology, Vol 4, Iss 3, p 035033 (2023)
In this manuscript we consider the problem of kernel classification. While worst-case bounds on the decay rate of the prediction error with the number of samples are known for some classifiers, they often fail to accurately describe the learning curv
Externí odkaz:
https://doaj.org/article/42957d087507457e8ac4fe235786ff15
Publikováno v:
Machine Learning: Science and Technology, Vol 4, Iss 2, p 025029 (2023)
Being able to reliably assess not only the accuracy but also the uncertainty of models’ predictions is an important endeavor in modern machine learning. Even if the model generating the data and labels is known, computing the intrinsic uncertainty
Externí odkaz:
https://doaj.org/article/26c1efbe1d28452ab5d3494938f78da9
Publikováno v:
Image Processing On Line, Vol 7, Pp 43-55 (2017)
In phase retrieval, the goal is to recover a complex signal from the magnitude of its linear measurements. While many well-known algorithms guarantee deterministic recovery of the unknown signal using i.i.d. random measurement matrices, they suffer s
Externí odkaz:
https://doaj.org/article/5fb209d3806a42a7bca1ead972a5e8ab
Publikováno v:
Physical Review X, Vol 10, Iss 4, p 041044 (2020)
Understanding the reasons for the success of deep neural networks trained using stochastic gradient-based methods is a key open problem for the nascent theory of deep learning. The types of data where these networks are most successful, such as image
Externí odkaz:
https://doaj.org/article/1a23fabc856f4ecb8c6ed721b923a393
Publikováno v:
Physical Review X, Vol 10, Iss 4, p 041037 (2020)
Reservoir computing is a relatively recent computational paradigm that originates from a recurrent neural network and is known for its wide range of implementations using different physical technologies. Large reservoirs are very hard to obtain in co
Externí odkaz:
https://doaj.org/article/f2ccc5e3b5054f3cb286dcedeabf9896
Autor:
Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová
Publikováno v:
Physical Review X, Vol 10, Iss 1, p 011057 (2020)
Gradient-descent-based algorithms and their stochastic versions have widespread applications in machine learning and statistical inference. In this work, we carry out an analytic study of the performance of the algorithm most commonly considered in p
Externí odkaz:
https://doaj.org/article/5be1ae79a5f941e3bce7b8ede2ac53b1
Deterministic and Generalized Framework for Unsupervised Learning with Restricted Boltzmann Machines
Publikováno v:
Physical Review X, Vol 8, Iss 4, p 041006 (2018)
Restricted Boltzmann machines (RBMs) are energy-based neural networks which are commonly used as the building blocks for deep-architecture neural architectures. In this work, we derive a deterministic framework for the training, evaluation, and use o
Externí odkaz:
https://doaj.org/article/84ae61f1c71443d8bb400019f21bbaa8
Publikováno v:
Journal of Statistical Mechanics: Theory and Experiment, 2022 (8)
Factorization of matrices where the rank of the two factors diverges linearly with their sizes has many applications in diverse areas such as unsupervised representation learning, dictionary learning or sparse coding. We consider a setting where the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aea2cf8bb034d396784c62244f43b621
https://hdl.handle.net/20.500.11850/564870
https://hdl.handle.net/20.500.11850/564870
Inverse probability problems whose generative models are given by strictly nonlinear Gaussian random fields show the all-or-nothing behavior: There exists a critical rate at which Bayesian inference exhibits a phase transition. Below this rate, the o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8cbb505fa2bb13296f8106871d68f8ad
http://arxiv.org/abs/2205.08782
http://arxiv.org/abs/2205.08782