Search Results for author: Yasser Roudi

Found 9 papers, 1 papers with code

Bayesian interpolation for power laws in neural data analysis

no code implementations18 Apr 2022 Iván A. Davidovich, Yasser Roudi

We discuss the implications of this result for the neural code in the V1 and offer the approach discussed here as a framework that future studies, perhaps exploring larger ranges of data, can employ as their starting point to examine power-law scalings in neural data.

Quantifying Relevance in Learning and Inference

no code implementations1 Feb 2022 Matteo Marsili, Yasser Roudi

This identifies samples obeying Zipf's law as the most compressed loss-less representations that are optimal in the sense of maximal relevance.

Restricted Boltzmann Machines as Models of Interacting Variables

no code implementations29 Mar 2021 Nicola Bulso, Yasser Roudi

We study the properties of these interactions in detail and evaluate how the accuracy with which the RBM approximates distributions over binary variables depends on the hidden node activation function and on the number of hidden nodes.

On the complexity of logistic regression models

no code implementations1 Mar 2019 Nicola Bulso, Matteo Marsili, Yasser Roudi

We investigate the complexity of logistic regression models which is defined by counting the number of indistinguishable distributions that the model can represent (Balasubramanian, 1997).

Model Selection regression

Minimum Description Length codes are critical

1 code implementation3 Sep 2018 Ryan John Cubero, Matteo Marsili, Yasser Roudi

We show that the codes that achieve optimal compression in MDL are critical in a very precise sense.

Methodology Data Analysis, Statistics and Probability

Variational perturbation and extended Plefka approaches to dynamics on random networks: the case of the kinetic Ising model

no code implementations28 Jul 2016 Ludovica Bachschmid-Romano, Claudia Battistin, Manfred Opper, Yasser Roudi

We first briefly consider the variational approach based on minimizing the Kullback-Leibler divergence between independent trajectories and the real ones and note that this approach only coincides with the mean field equations from the saddle point approximation to the generating functional when the dynamics is defined through a logistic link function, which is the case for the kinetic Ising model with parallel update.

Sparse model selection in the highly under-sampled regime

no code implementations3 Mar 2016 Nicola Bulso, Matteo Marsili, Yasser Roudi

We propose a method for recovering the structure of a sparse undirected graphical model when very few samples are available.

Model Selection

Learning with hidden variables

no code implementations1 Jun 2015 Yasser Roudi, Graham Taylor

Learning and inferring features that generate sensory input is a task continuously performed by cortex.

Ising Models for Inferring Network Structure From Spike Data

no code implementations9 Jun 2011 John Hertz, Yasser Roudi, Joanna Tyrcha

Now that spike trains from many neurons can be recorded simultaneously, there is a need for methods to decode these data to learn about the networks that these neurons are part of.

Cannot find the paper you are looking for? You can Submit a new open access paper.