Skip to search formSkip to main contentSkip to account menu

Backpropagation through structure

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

Related topics

Related topics

3 relations
Backpropagation through timeRecurrent neural networkRecursive neural network

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
2013
2013
Improvement of panchromatic IKONOS image classification based on structural neural network
  • Weibao Zou
  • IEEE Geoscience and Remote Sensing Symposium
  • 2013
  • Corpus ID: 39609746
Remote sensing image classification plays an important role in urban studies. This work presents a method for panchromatic image… 
2013
2013
On the correspondence between neural folding architectures and tree automata
The folding architecture together with adequate supervised training algorithms is a special recurrent neural network model… 
2002
2002
Robust learning in adaptive processing of data structures for tree representation based image classification
In this paper, novel robust learning in adaptive processing of data structures for tree representation based image classification… 
1995
1995
Fakult¨at F ¨ Ur Informatik Der Technischen Universität M ¨ Unchen Lehrstuhl Viii Forschungsgruppe Automated Reasoning Learning Task-dependent Distributed Representations by Backpropagation through…
b b b b b b b b b b b b b b b b b b b Abstract While neural networks are very successfully applied to the processing of xed… 
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)