articles
None
view repo
Deep Learning's recent successes have mostly relied on Convolutional Networks, which exploit fundamental statistical properties of images, sounds and video data: the local stationarity and multi-scale compositional structure, that allows expressing long range interactions in terms of shorter, localized interactions. However, there exist other important examples, such as text documents or bioinformatic data, that may lack some or all of these strong statistical regularities. In this paper we consider the general question of how to construct deep architectures with small learning complexity on general non-Euclidean domains, which are typically unknown and need to be estimated from the data. In particular, we develop an extension of Spectral Networks which incorporates a Graph Estimation procedure, that we test on large-scale classification problems, matching or improving over Dropout Networks with far less parameters to estimate.
READ FULL TEXT
Recently, neural network based approaches have achieved significant
impr...
read it
We propose the Lanczos network (LanczosNet), which uses the Lanczos algo...
read it
Deep convolutional networks provide state of the art classifications and...
read it
Graph Convolutional Networks (GCNs) generalize the idea of deep convolut...
read it
In this work, we are interested in generalizing convolutional neural net...
read it
Recent advances in graph convolutional networks have significantly impro...
read it
The superior performance of deep convolutional networks over high-dimens...
read it
None
Comments
There are no comments yet.