Abstract
While neural networks are very successfully applied to the processing of fixed-length vectors and variable-length sequences, the current state of the art does not allow the efficient processing of structured objects of arbitrary shape (like logical terms, trees or graphs). We present a connectionist architecture together with a novel supervised learning scheme which is capable of solving inductive inference tasks on complex symbolic structures of arbitrary size. The most general structures that can be handled are labeled directed acyclic graphs. The major difference of our approach compared to others is that the structure-representations are exclusively tuned for the intended inference task. Our method is applied to tasks consisting in the classification of logical terms. These range from the detection of a certain subterm to the satisfaction of a specific unification pattern. Compared to previously known approaches we obtained superior results in that domain.
Keywords
UnificationComputer scienceConnectionismInferenceTask (project management)BackpropagationTheoretical computer scienceArtificial intelligenceRange (aeronautics)Directed acyclic graphArtificial neural networkInductive biasDomain (mathematical analysis)AlgorithmMulti-task learningMathematics
Affiliated Institutions
Related Publications
A Comparison between Recursive Neural Networks and Graph Neural Networks
Recursive neural networks (RNNs) and graph neural networks (GNNs) are two connectionist models that can directly process graphs. RNNs and GNNs exploit a similar processing frame...
Neural Network for Graphs: A Contextual Constructive Approach
This paper presents a new approach for learning in structured domains (SDs) using a constructive neural network for graphs (NN4G). The new model allows the extension of the inpu...
The Graph Neural Network Model
Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and dat...
Neural GPUs Learn Algorithms
Abstract: Learning an algorithm from examples is a fundamental problem that has been widely studied. Recently it has been addressed using neural networks, in particular by Neura...
Connectionist models of recognition memory: Constraints imposed by learning and forgetting functions.
Multilayer connectionist models of memory based on the encoder model using the backpropagation learning rule are evaluated. The models are applied to standard recognition memory...
Publication Info
- Year
- 2002
- Type
- article
- Volume
- 1
- Pages
- 347-352
- Citations
- 591
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
591
OpenAlex
Cite This
Christoph Goller,
Andreas Küchler
(2002).
Learning task-dependent distributed representations by backpropagation through structure.
Proceedings of International Conference on Neural Networks (ICNN'96)
, 1
, 347-352.
https://doi.org/10.1109/icnn.1996.548916
Identifiers
- DOI
- 10.1109/icnn.1996.548916