Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Encoding and Decoding Representations with Sum- and Max-Product Networks
Antonio Vergari, Robert Peharz, Nicola Di Mauro, Floriana Esposito
Feb 17, 2017 (modified: Mar 10, 2017)ICLR 2017 workshop submissionreaders: everyone
Abstract: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.
TL;DR:Sum-Product Networks can be effectively employed for unsupervised representation learning, when turned into Max-Product Networks, they can also be used as encoder-decoders