activity
20102026
most citedOn the Number of Linear Regions of Deep Neural Networks

832 citations · 1.3k across the 79 of their papers we have counts for

collaborators
Showing 2014Show all

7 papers · 1 filter

stat.ML2014★ 6 cited

Deep Narrow Boltzmann Machines are Universal Approximators

Guido Montufar

We show that deep narrow Boltzmann machines are universal approximators of probability distributions on the activities of their visible units, provided they have sufficiently many…

cs.IT2014

Sequential Recurrence-Based Multidimensional Universal Source Coding of Lempel-Ziv Type

Tyll Krueger, Guido Montufar, Ruedi Seiler +1

We define an algorithm that parses multidimensional arrays sequentially into mainly unrepeated but nested multidimensional sub-arrays of increasing size, and show that the resultin…

eess.SY2014★ 30 cited

A Theory of Cheap Control in Embodied Systems

Guido Montufar, Keyan Ghazi-Zahedi, Nihat Ay

We present a framework for designing cheap control architectures for embodied agents. Our derivation is guided by the classical problem of universal approximation, whereby we explo…

stat.ML2014★ 40 cited

Expressive Power and Approximation Errors of Restricted Boltzmann Machines

Guido Montufar, Johannes Rauh, Nihat Ay

We present explicit classes of probability distributions that can be learned by Restricted Boltzmann Machines (RBMs) depending on the number of units that they contain, and which a…

math.DG2014★ 14 cited

On the Fisher Metric of Conditional Probability Polytopes

Guido Montufar, Johannes Rauh, Nihat Ay

We consider three different approaches to define natural Riemannian metrics on polytopes of stochastic matrices. First, we define a natural class of stochastic maps between these p…

cs.NE2014★ 10 cited

Geometry and Expressive Power of Conditional Restricted Boltzmann Machines

Guido Montufar, Nihat Ay, Keyan Ghazi-Zahedi

Conditional restricted Boltzmann machines are undirected stochastic neural networks with a layer of input and output units connected bipartitely to a layer of hidden units. These n…

stat.ML2014★ 832 cited

On the Number of Linear Regions of Deep Neural Networks

Guido Montúfar, Razvan Pascanu, Kyunghyun Cho +1

We study the complexity of functions computable by deep feedforward neural networks with piecewise linear activations in terms of the symmetries and the number of linear regions th…