Why Distributed Representation is Inherently Non-Symbolic

1990 ◽  
pp. 58-66 ◽  
Author(s):  
Tim van Gelder
Keyword(s):  
Distributed Representation

Unification using a distributed representation

1994 ◽  
Vol 5 (2) ◽  
pp. 5-7 ◽  
Author(s):  
A. Browne ◽  
J. Pilkington
Keyword(s):  
Distributed Representation

scholarly journals Multi-Scale Distributed Representation for Deep Learning and its Application to b-Jet Tagging

2018 ◽  
Vol 72 (11) ◽  
pp. 1292-1300
Author(s):  
Jason Sang Hun Lee ◽  
Inkyu Park ◽  
Sangnam Park
Keyword(s):  
Deep Learning ◽  
Distributed Representation ◽  
Multi Scale

scholarly journals Action recognition from a distributed representation of pose and appearance

CVPR 2011 ◽  
2011 ◽  
Author(s):  
Subhransu Maji ◽  
Lubomir Bourdev ◽  
Jitendra Malik
Keyword(s):  
Action Recognition ◽  
Distributed Representation

scholarly journals Clustering-Based Relational Unsupervised Representation Learning with an Explicit Distributed Representation

2017 ◽  
Author(s):  
Sebastijan Dumancic ◽  
Hendrik Blockeel
Keyword(s):  
Relational Learning ◽  
Representation Learning ◽  
Relational Data ◽  
Distributed Representation ◽  
Learning Tasks ◽  
Wide Range ◽  
Lower Complexity ◽  
Classification Tasks ◽  
Latent Representations

The goal of unsupervised representation learning is to extract a new representation of data, such that solving many different tasks becomes easier. Existing methods typically focus on vectorized data and offer little support for relational data, which additionally describes relationships among instances. In this work we introduce an approach for relational unsupervised representation learning. Viewing a relational dataset as a hypergraph, new features are obtained by clustering vertices and hyperedges. To find a representation suited for many relational learning tasks, a wide range of similarities between relational objects is considered, e.g. feature and structural similarities. We experimentally evaluate the proposed approach and show that models learned on such latent representations perform better, have lower complexity, and outperform the existing approaches on classification tasks.

Sign in / Sign up

Export Citation Format

Share Document