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 2015Show all

5 papers · 1 filter

cs.AI2015★ 28 cited

Evaluating Morphological Computation in Muscle and DC-motor Driven Models of Human Hopping

Keyan Ghazi-Zahedi, Daniel F. B. Haeufle, Guido Montufar +2

In the context of embodied artificial intelligence, morphological computation refers to processes which are conducted by the body (and environment) that otherwise would have to be…

stat.ML2015

Dimension of Marginals of Kronecker Product Models

Guido Montufar, Jason Morton

A Kronecker product model is the set of visible marginal probability distributions of an exponential family whose sufficient statistics matrix factorizes as a Kronecker product of…

math.PR2015

Hierarchical Models as Marginals of Hierarchical Models

Guido Montufar, Johannes Rauh

We investigate the representation of hierarchical models in terms of marginals of other hierarchical models with smaller interactions. We focus on binary variables and marginals of…

math.OC2015★ 7 cited

Geometry and Determinism of Optimal Stationary Control in Partially Observable Markov Decision Processes

Guido Montufar, Keyan Ghazi-Zahedi, Nihat Ay

It is well known that for any finite state Markov decision process (MDP) there is a memoryless deterministic policy that maximizes the expected reward. For partially observable Mar…

math.CO2015

Mode Poset Probability Polytopes

Guido Montufar, Johannes Rauh

A mode of a probability vector is a local maximum with respect to some vicinity structure on the set of elementary events. The mode inequalities cut out a polytope from the simplex…