English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We introduce Graph-Structured Sum-Product Networks (GraphSPNs), aprobabilistic approach to structured prediction for problems where dependenciesbetween latent variables are expressed in terms of arbitrary, dynamic graphs.While many approaches to structured prediction place strict constraints on theinteractions between inferred variables, many real-world problems can be onlycharacterized using complex graph structures of varying size, oftencontaminated with noise when obtained from real data. Here, we focus on onesuch problem in the domain of robotics. We demonstrate how GraphSPNs can beused to bolster inference about semantic, conceptual place descriptions usingnoisy topological relations discovered by a robot exploring large-scale officespaces. Through experiments, we show that GraphSPNs consistently outperform thetraditional approach based on undirected graphical models, successfullydisambiguating information in global semantic maps built from uncertain, noisylocal evidence. We further exploit the probabilistic nature of the model toinfer marginal distributions over semantic descriptions of as yet unexploredplaces and detect spatial environment configurations that are novel andincongruent with the known evidence.

Learning Graph-Structured Sum-Product Networks for Probabilistic Semantic Maps