Supervised neural networks for the classification of structures

1997/05/01 by Alessandro Sperduti, A. Sperduti, A. Starita +1 · 30 citations
Computer Science · Engineering · #Fault Detection and Control Systems #Fuzzy Logic and Control Systems #Neural Networks and Applications

paper · doi:10.1109/72.572108

openalex publication_date 1997/05/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30

Abstract

Standard neural networks and statistical methods are usually believed to be inadequate when dealing with complex structures because of their feature-based approach. In fact, feature-based approaches usually fail to give satisfactory solutions because of the sensitivity of the approach to the a priori selection of the features, and the incapacity to represent any specific information on the relationships among the components of the structures. However, we show that neural networks can, in fact, represent and classify structured patterns. The key idea underpinning our approach is the use of the so called "generalized recursive neuron", which is essentially a generalization to structures of a recurrent neuron. By using generalized recursive neurons, all the supervised networks developed for the classification of sequences, such as backpropagation through time networks, real-time recurrent networks, simple recurrent networks, recurrent cascade correlation networks, and neural trees can, on the whole, be generalized to structures. The results obtained by some of the above networks (with generalized recursive neurons) on the classification of logic terms are presented.

Citations

• Finding Structure in Time

Cited by

• Structural Invariance Matters: Rethinking Graph Rewiring through Graph Metrics
• Enhancing Graph Neural Networks: A Mutual Learning Approach
• Axial Neural Networks for Dimension-Free Foundation Models
• How Bad Is Forming Your Own Multidimensional Opinion?
• Agentic Graph Neural Networks for Wireless Communications and Networking Towards Edge General Intelligence: A Survey
• Online Continual Graph Learning
• Boosting Team Modeling through Tempo-Relational Representation Learning
• New results on recurrent network training: unifying the algorithms and accelerating convergence
• A Gentle Introduction to Deep Learning for Graphs
• CCNet: Criss-Cross Attention for Semantic Segmentation
• Graph Neural Networks for Node-Level Predictions
• HEIMDALL: a grapH-based sEIsMic Detector And Locator for microseismicity
• A Lagrangian Approach to Information Propagation in Graph Neural Networks
• Understanding Generalization in Node and Link Prediction
• Adaptive Generation of Phantom Limbs Using Visible Hierarchical Autoencoders
• Reconstruction for Powerful Graph Representations
• Discovering Supply Chain Links with Augmented Intelligence
• SAG-VAE: End-to-end Joint Inference of Data Representations and Feature Relations
• Some Algorithms on Exact, Approximate and Error-Tolerant Graph Matching
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Flow-Attentional Graph Neural Networks
• A Survey on The Expressive Power of Graph Neural Networks
• Equivariant Subgraph Aggregation Networks
• Graph Element Networks: adaptive, structured computation and memory
• Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning
• Isometric Transformation Invariant and Equivariant Graph Convolutional Networks
• H2CGL: Modeling dynamics of citation network for impact prediction
• Utilising Graph Machine Learning within Drug Discovery and Development
• Ripple Walk Training: A Subgraph-based training framework for Large and Deep Graph Neural Network
• Representation, learning, and planning algorithms for geometric task and motion planning