Recurrent networks for structured data - A unifying approach and its properties

Authors:
Barbara Hammer
Affiliations:
Universität Osnabrück, Department of Mathematics/Computer Science, D-49069 Osnabrück, Germany
Venue:
Cognitive Systems Research
Year:
2002

Citing 24
Cited 7

A theory of the learnable

Communications of the ACM
Multilayer feedforward networks are universal approximators

Neural Networks
Review of neural networks for speech recognition

Neural Computation
What size net gives valid generalization?

Neural Computation
Recursive distributed representations

Artificial Intelligence - On connectionist symbol processing
Tensor product variable binding and the representation of symbolic structures in connectionist systems

Artificial Intelligence - On connectionist symbol processing
Analog computation via neural networks

Theoretical Computer Science
Computability with low-dimensional dynamical systems

Theoretical Computer Science
Gradient-based learning algorithms for recurrent networks and their computational complexity

Backpropagation
Extraction of rules from discrete-time recurrent neural networks

Neural Networks
The dynamic universality of sigmoidal neural networks

Information and Computation
Constructing deterministic finite-state automata in recurrent neural networks

Journal of the ACM (JACM)
Back-propagation is not efficient

Neural Networks
On the effect of analog noise in discrete-time analog computations

Neural Computation
Learning with Recurrent Neural Networks

Learning with Recurrent Neural Networks
Advances in SHRUTI—A Neurally Motivated Model of RelationalKnowledge Representation and Rapid Inference Using Temporal Synchrony

Applied Intelligence
Symbolic Interpretation of Artificial Neural Networks

IEEE Transactions on Knowledge and Data Engineering
Simple Strategies to Encode Tree Automata in Sigmoid Recursive Neural Networks

IEEE Transactions on Knowledge and Data Engineering
Generalization Ability of Folding Networks

IEEE Transactions on Knowledge and Data Engineering
On the Generalization Ability of Recurrent Networks

ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Neural Networks for Adaptive Processing of Structured Data

ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
On Approximate Learning by Multi-layered Feedforward Circuits

ALT '00 Proceedings of the 11th International Conference on Algorithmic Learning Theory
A Competitive-Layer Model for Feature Binding and Sensory Segmentation

Neural Computation
The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction

Neural Computation

Architectural bias in recurrent neural networks: fractal analysis

Neural Computation
Recursive self-organizing network models

Neural Networks - 2004 Special issue: New developments in self-organizing systems
From Hopfield nets to recursive networks to graph machines: numerical machine learning for structured data

Theoretical Computer Science
A flexible multi-layer self-organizing map for generic processing of tree-structured data

Pattern Recognition
Original article: Learning over sets with Recurrent Neural Networks: An empirical categorization of aggregation functions

Mathematics and Computers in Simulation
Graph machines and their applications to computer-aided drug design: a new approach to learning from structured data

UC'06 Proceedings of the 5th international conference on Unconventional Computation
Perspectives of self-adapted self-organizing clustering in organic computing

BioADIT'06 Proceedings of the Second international conference on Biologically Inspired Approaches to Advanced Information Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

We consider recurrent neural networks which deal with symbolic formulas, terms, or, generally speaking, tree-structured data. Approaches like the recursive autoassociative memory, discrete-time recurrent networks, folding networks, tensor construction, holographic reduced representations, and recursive reduced descriptions fall into this category. They share the basic dynamics of how structured data are processed: the approaches recursively encode symbolic data into a connectionistic representation or decode symbolic data from a connectionistic representation by means of a simple neural function. In this paper, we give an overview of the ability of neural networks with these dynamics to encode and decode tree-structured symbolic data. The correlated tasks, approximating and learning mappings where the input domain or the output domain may consist of structured symbolic data, are examined as well.