Search Results for author:
Found 17 papers, 7 papers with code
Predicting large scale cosmological structure evolution with GAN-based autoencoders
Cosmological simulations play a key role in the prediction and understanding of large scale structure formation from initial conditions.
Inferring effective couplings with Restricted Boltzmann Machines
Generative models offer a direct way of modeling complex data.
The Copycat Perceptron: Smashing Barriers Through Collective Learning
We characterize the equilibrium properties of a model of $y$ coupled binary perceptrons in the teacher-student scenario, subject to a learning rule, with an explicit ferromagnetic coupling proportional to the Hamming distance between the students' weights.
Fast and Functional Structured Data Generators Rooted in Out-of-Equilibrium Physics
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.
Unsupervised hierarchical clustering using the learning dynamics of RBMs
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.
Explaining the effects of non-convergent sampling in the training of Energy-Based Models
In this paper, we quantify the impact of using non-convergent Markov chains to train Energy-Based models (EBMs).
Thermodynamics of bidirectional associative memories
Introduced by Kosko in 1988 as a generalization of the Hopfield model to a bipartite structure, the simplest architecture is defined by two layers of neurons, with synaptic connections only between units of different layers: even without internal connections within each layer, information storage and retrieval are still possible through the reverberation of neural activities passing from one layer to another.
Learning a Restricted Boltzmann Machine using biased Monte Carlo sampling
Moreover, we show that this sampling technique can also be used to improve the computation of the log-likelihood gradient during training, leading to dramatic improvements in training RBMs with artificial clustered datasets.
Regularization of Mixture Models for Robust Principal Graph Learning
A regularized version of Mixture Models is proposed to learn a principal graph from a distribution of $D$-dimensional data points.
Equilibrium and non-Equilibrium regimes in the learning of Restricted Boltzmann Machines
In this work, we show that this mixing time plays a crucial role in the dynamics and stability of the trained model, and that RBMs operate in two well-defined regimes, namely equilibrium and out-of-equilibrium, depending on the interplay between this mixing time of the model and the number of steps, $k$, used to approximate the gradient.
Restricted Boltzmann Machine, recent advances and mean-field theory
This review deals with Restricted Boltzmann Machine (RBM) under the light of statistical physics.
Encoding large scale cosmological structure with Generative Adversarial Networks
We find that the GAN successfully generates new images that are statistically consistent with the images it was trained on.
Robust Multi-Output Learning with Highly Incomplete Data via Restricted Boltzmann Machines
In order to take full advantage of these dependencies we consider a purely probabilistic setting in which the features imputation and multi-label classification problems are jointly solved.
Gaussian-Spherical Restricted Boltzmann Machines
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.
Learning a Local Symmetry with Neural-Networks
We explore the capacity of neural networks to detect a symmetry with complex local and non-local patterns : the gauge symmetry Z 2 .
Thermodynamics of Restricted Boltzmann Machines and related learning dynamics
In the non-linear regime, instead, the selected modes interact and eventually impose a matching of the order parameters to their empirical counterparts estimated from the data.
Spectral Dynamics of Learning Restricted Boltzmann Machines
This let us show how in the linear regime, in which the RBM is found to operate at the beginning of the training, the statistical properties of the data drive the selection of the unstable modes of the weight matrix.
