Inductive learning in symbolic domains using structure-driven recurrent neural networks

Küchler, Andreas; Goller, Christoph

doi:10.1007/3-540-61708-6_60

Cited by 26 publications

(24 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RNNs have been used in some applications including medical and technical diagnoses, molecular biology and chemistry, geometrical and spatial reasoning, speech and language processing [12], [18]. Figure 1(a) illustrates the structure of the generalized recursive neuron.…”

Section: Recursive Neural Networkmentioning

confidence: 99%

Self-learning recursive neural networks for structured data classification

Bouchachia

Ortner

2014

2014 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Automatic classification of structured data is a challenging task and its relevance to many domains is evident. However, collecting labeled data may turn to be a quite expensive task and sometimes even prone to mislabeling. A technical solution to this problem consists in combining few labeled data samples and a significant amount of unlabeled data samples to train a classifier. Likewise, the present paper deals with the classification of partially labeled tree-like structured data. To carry on this task, we suggest an adapted variant of recursive neural networks (RNNs) that is equipped with semi-supervision mechanisms capable of learning from labeled and unlabeled tree-like data. Accordingly RNNs rely on selflearning to actively pre-label data which will be combined with originally labeled one during the learning process. The semi-supervised RNNs approach is presented and evaluated on real-world eXtensible Markup Language (XML) collection of documents in the context of digital libraries. The initial empirical experiments show high quality results.

show abstract

Section: Recursive Neural Networkmentioning

confidence: 99%

Self-learning recursive neural networks for structured data classification

Bouchachia

Ortner

2014

2014 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…States described by logic formulas can be represented by trees. The folding architecture network (Küchler and Goller 1996, Goller 1997, Küchler 1999 is closely related to the recurrent neural network and RAAM (Pollack 1990, Sperduti 1994. It allows the representation of labelled trees.…”

Section: N Oisementioning

confidence: 99%

Pictorial reasoning with cell assemblies

Wichert¹

2001

Connection Science

View full text Add to dashboard Cite

A bstract. We introduce a biologically and psychologically plausible neuronal model which could explain how pictorial reasoning is carried out by the human brain. This biologically inspired model throws some light on how some problem-solving abilities might actually be performed by the human brain using neural cell assemblies. It also highlights the bene ts of distributed representation. These bene ts include the ability to learn from experience, heuristics resulting from picture representation and the ability to deal with noisy information. The description of the reasoning process by formation of associations gives exibility and power in operation. The proper way to use it, the proper data representations and the proper network architecture are presented in this paper.

show abstract

“…In the theorem prover example the structure is the family of syntactical trees representing partial proof attempts, and the ultimate goal is a map from any proof attempt to a rating for scoring a candidate next move in the associate decision tree. The above representations in input to the scoring network can be suitably synthesized either within the LRAAM strategy in [27] or by a structured neural network like in [51] and [69].…”

Section: Computational Flowmentioning

confidence: 99%

Sub-symbolically managing pieces of symbolical functions for sorting

Apolloni

Zoppis

1999

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

We present a hybrid system for managing both symbolic and subsymbolic knowledge in a uniform way. Our aim is to solve problems where some gap in formal theories occurs which stops us from getting a fully symbolical solution. The idea is to use neural modules to functionally connect pieces of symbolical knowledge, such as mathematical formulas and deductive rules. The whole system is trained through a backpropagation learning algorithm where all (symbolic or subsymbolic) free parameters are updated piping back the error through each component of the system. The structure of this system is very general, possibly varying over time, possibly managing fuzzy variables and decision trees. We use as a test-bed the problem of sorting a file, where suitable suggestions on next sorting moves are supplied by the network also on the basis of hints provided by some conventional sorters. A comprehensive discussion of system performance is provided in order to understand behaviors and capabilities of the proposed hybrid system.

show abstract

Inductive learning in symbolic domains using structure-driven recurrent neural networks

Cited by 26 publications

References 6 publications

Self-learning recursive neural networks for structured data classification

Self-learning recursive neural networks for structured data classification

Pictorial reasoning with cell assemblies

Sub-symbolically managing pieces of symbolical functions for sorting

Contact Info

Product

Resources

About