Backpropagation through structure

Backpropagation Through Structure (BPTS) is a gradient-based technique for training recursive neural nets (a superset of recurrent neural nets) and… (More)
Wikipedia

Topic mentions per year

Topic mentions per year

1996-2012
01219962012

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
2013
2013
  • Weibao Zou
  • 2014 IEEE Geoscience and Remote Sensing Symposium
  • 2013
Remote sensing image classification plays an important role in urban studies. This work presents a method for panchromatic image… (More)
  • figure 1
  • figure 2
  • figure 4
  • table 1
Is this relevant?
2012
2012
Remote sensing image classification plays an important role in a variety of urban studies. This study presents a method for… (More)
  • figure 1
  • figure 3
  • figure 2
  • figure 4
  • table I
Is this relevant?
2008
2008
A structured-based neural network (NN) with backpropagation through structure (BPTS) algorithm is conducted for image… (More)
  • figure 1
  • figure 2
  • figure 3
  • table 1
  • table 2
Is this relevant?
2003
2003
Many researchers have explored the use of neural network models for the adaptive processing of data structures. The learning… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • figure 5
Is this relevant?
2003
2003
Many researchers have explored the use of neural-network representations for the adaptive processing of data structures. One of… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • figure 5
Is this relevant?
1999
1999
There are several challenging real-world problems, for instance in the fields of medical and technical diagnosis, molecular… (More)
  • figure 1.2
  • figure 3.3
  • figure 3.7
  • figure 4.5
  • figure 4.6
Is this relevant?
1998
1998
  • Andreas K Uchler
  • 1998
The folding architecture together with adequate supervised training algorithms is a special recurrent neural network model… (More)
Is this relevant?
1997
1997
In the last few years it has been shown that recurrent neural networks are adequate for processing general data structures like… (More)
  • figure 5
Is this relevant?
Highly Cited
1996
Highly Cited
1996
While neural networks are very successfully applied to the processing of xed-length vectors and variable-length sequences, the… (More)
Is this relevant?