G
Guido Montúfar
Researcher at University of California, Los Angeles
Publications - 129
Citations - 3085
Guido Montúfar is an academic researcher from University of California, Los Angeles. The author has contributed to research in topics: Computer science & Probability distribution. The author has an hindex of 21, co-authored 111 publications receiving 2538 citations. Previous affiliations of Guido Montúfar include Max Planck Society & Pennsylvania State University.
Papers
More filters
Posted Content
On the Number of Linear Regions of Deep Neural Networks
TL;DR: 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 that they have is investigated.
Proceedings Article
On the Number of Linear Regions of Deep Neural Networks
TL;DR: In this article, the authors 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 that they have.
Posted Content
On the number of response regions of deep feed forward networks with piece-wise linear activations
TL;DR: In this paper, the complexity of deep feedforward networks with linear pre-synaptic couplings and rectified linear activations is compared with a single layer version of the model.
Journal ArticleDOI
Refinements of universal approximation results for deep belief networks and restricted boltzmann machines
Guido Montúfar,Nihat Ay +1 more
TL;DR: It is shown that any distribution on the set of binary vectors of length can be arbitrarily well approximated by an RBM with hidden units, and this confirms a conjecture presented in Le Roux and Bengio (2010).
Posted Content
Refinements of Universal Approximation Results for Deep Belief Networks and Restricted Boltzmann Machines
Guido Montúfar,Nihat Ay +1 more
TL;DR: In this article, it was shown that any distribution p on the set of binary vectors of length n can be arbitrarily well approximated by an RBM with k-1 hidden units, where k is the minimal number of pairs of binary vector differing in only one entry such that their union contains the support set of p.