© 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings. All Rights Reserved. Sum-Product Networks (SPNs) are deep density estimators allowing exact and tractable inference. While up to now SPNs have been employed as black-box inference machines, we exploit them as feature extractors for unsupervised Representation Learning. Representations learned by SPNs are rich probabilistic and hierarchical part-based features. SPNs converted into Max-Product Networks (MPNs) provide a way to decode these representations back to the original input space. In extensive experiments, SPN and MPN encoding and decoding schemes prove highly competitive for Multi-Label Classification tasks
In several domains obtaining class annotations is expensive while at the same time unlabelled data a...
Sum-product networks allow to model complex variable interactions while still granting efficient inf...
Discriminatively-trained probabilistic models often outperform their generative counterparts on chal...
Sum-Product Networks (SPNs) are deep tractable probabilistic models by which several kinds of infere...
Sum-Product Networks (SPNs) are a deep probabilistic architecture that up to now has been successful...
Sum-Product Networks (SPNs) are a deep probabilistic architecture that up to now has been successful...
Copyright © 2018, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rig...
Sum-product networks (SPNs) are a recently developed class of deep probabilistic models where infere...
Sum-Product Networks (SPNs) were recently proposed as a new class of probabilistic graphical models ...
Sum-product networks (SPNs) are a recently-proposed deep architecture that guarantees tractable infe...
The need for feasible inference in Probabilistic Graphical Models (PGMs) has lead to tractable model...
Sum-Product Networks (SPNs) and their credal counterparts are machine learning models that combine g...
The sum-product network (SPN) is a recently-proposed deep model consisting of a network of sum and p...
Sum-product networks (SPNs) are expressive probabilistic models with a rich set of exact and efficie...
The sum-product network (SPN) is a recently-proposed deep model consisting of a network of sum and p...
In several domains obtaining class annotations is expensive while at the same time unlabelled data a...
Sum-product networks allow to model complex variable interactions while still granting efficient inf...
Discriminatively-trained probabilistic models often outperform their generative counterparts on chal...
Sum-Product Networks (SPNs) are deep tractable probabilistic models by which several kinds of infere...
Sum-Product Networks (SPNs) are a deep probabilistic architecture that up to now has been successful...
Sum-Product Networks (SPNs) are a deep probabilistic architecture that up to now has been successful...
Copyright © 2018, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rig...
Sum-product networks (SPNs) are a recently developed class of deep probabilistic models where infere...
Sum-Product Networks (SPNs) were recently proposed as a new class of probabilistic graphical models ...
Sum-product networks (SPNs) are a recently-proposed deep architecture that guarantees tractable infe...
The need for feasible inference in Probabilistic Graphical Models (PGMs) has lead to tractable model...
Sum-Product Networks (SPNs) and their credal counterparts are machine learning models that combine g...
The sum-product network (SPN) is a recently-proposed deep model consisting of a network of sum and p...
Sum-product networks (SPNs) are expressive probabilistic models with a rich set of exact and efficie...
The sum-product network (SPN) is a recently-proposed deep model consisting of a network of sum and p...
In several domains obtaining class annotations is expensive while at the same time unlabelled data a...
Sum-product networks allow to model complex variable interactions while still granting efficient inf...
Discriminatively-trained probabilistic models often outperform their generative counterparts on chal...