Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Monasson, R��mi"'
Restricted Boltzmann Machines (RBM) are bi-layer neural networks used for the unsupervised learning of model distributions from data. The bipartite architecture of RBM naturally defines an elegant sampling procedure, called Alternating Gibbs Sampling
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b0bc54e03b7bcd63c0e762ce74e4a634
Autor:
Fanthomme, Arnaud, Monasson, R��mi
We study the learning dynamics and the representations emerging in Recurrent Neural Networks trained to integrate one or multiple temporal signals. Combining analytical and numerical investigations, we characterize the conditions under which a RNN wi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::86774bfbad6013914368b0dd402c8ec8
Autor:
Battista, Aldo, Monasson, R��mi
Recurrent neural networks (RNN) are powerful tools to explain how attractors may emerge from noisy, high-dimensional dynamics. We study here how to learn the ~N^(2) pairwise interactions in a RNN with N neurons to embed L manifolds of dimension D <<
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d7bddfc125b970700d7009e6c9811f96
A Restricted Boltzmann Machine (RBM) is an unsupervised machine-learning bipartite graphical model that jointly learns a probability distribution over data and extracts their relevant statistical features. As such, RBM were recently proposed for char
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6d5af3daec7c1b82b4acf3de4db7428e
Statistical analysis of evolutionary-related protein sequences provides insights about their structure, function, and history. We show that Restricted Boltzmann Machines (RBM), designed to learn complex high-dimensional data and their statistical fea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5feb9c96dce48f6a0ac051b89bbf517a
Autor:
Tubiana, J��r��me, Monasson, R��mi
Extracting automatically the complex set of features composing real high-dimensional data is crucial for achieving high performance in machine--learning tasks. Restricted Boltzmann Machines (RBM) are empirically known to be efficient for this purpose
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f8594ee9743cef99118c505be9ca90e1
Autor:
Monasson, R��mi
The problem of infering the top component of a noisy sample covariance matrix with prior information about the distribution of its entries is considered, in the framework of the spiked covariance model. Using the replica method of statistical physics
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::125c8ac080df6d830f63143d2c15066d
Autor:
Monasson, R��mi, Villamaina, Dario
We consider the problem of estimating the principal components of a population correlation matrix from a limited number of measurement data. Using a combination of random matrix and information-theoretic tools, we show that all the eigenmodes of the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::96107e53bde6c29b3a611b40ff889bbb
Autor:
Monasson, R��mi, Rosay, Sophie
We study the stable phases of an attractor neural network model, with binary units, for hippocampal place cells encoding 1D or 2D spatial maps or environments. Using statistical mechanics tools we show that, below critical values for the noise in the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d235c20316837f0362cbdccb0982df50
Autor:
Monasson, R��mi, Rosay, Sophie
The dynamics of a neural model for hippocampal place cells storing spatial maps is studied. In the absence of external input, depending on the number of cells and on the values of control parameters (number of environments stored, level of neural noi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d6f0a4b4ad895325540796d027488e5