Pairwise Coupling of Convolutional Neural Networks for the Better Explainability of Classification Systems

Ensembling techniques are viewed as a promising machine learning tool to resolve issues arising from the monolithic nature of deep neural networks. In this paper, we consider pairwise coupling models built from neural networks, which is a special kind of ensemble. These models promise to provide much needed modularity in classification models employing deep networks. In order to be practical, pairwise coupling models have to have comparable memory and speed requirements to commonly used architectures. In this paper, we propose novel architectures that address this key problem of pairwise coupling models. We show that the classification accuracy of the resulting pairwise coupling models matches the original network, while exceeding the original network’s pairwise accuracy. The introduction of these pairwise models brings additional benefits. First, they allow for much less expensive uncertainty predictions. Secondly, their modularity allows for the fine-tuning of classification accuracy. Both of these benefits can be viewed as relating to the larger topic of improving the explainability as well as the modularity of deep neural networks.

• Publication year

  2025

• Venue

  Applied Sciences

• Publication date

  2025-11-12

• Fields of study

  Not labeled

• Identifiers
  DOI 10.3390/app152212007
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• An analysis of explainability methods for convolutional neural networks

  2023cited by this paper
• Explainable Convolutional Neural Networks: A Taxonomy, Review, and Future Directions

  2022cited by this paper
• A novel explainable neural network for Alzheimer's disease diagnosis

  2022cited by this paper
• Explainability of deep neural networks for MRI analysis of brain tumors

  2022cited by this paper
• A survey of uncertainty in deep neural networks

  2021cited by this paper
• A Survey on Neural Network Interpretability

  2020cited by this paper
• Neural Network-Based Uncertainty Quantification: A Survey of Methodologies and Applications

  2018cited by this paper
• Classification by pairwise coupling of imprecise probabilities

  2018cited by this paper
• Bayes covariant multi-class classification

  2016cited by this paper
• Deep Learning

  2016cited by this paper
• “Why Should I Trust You?”: Explaining the Predictions of Any Classifier

  2016cited by this paper
• An Introduction to Statistical Learning

  2013cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• LIBSVM: A library for support vector machines

  2011cited by this paper
• Probability Estimates for Multi-class Classification by Pairwise Coupling

  2003cited by this paper
• Artificial Neural Networks — ICANN 2001

  2001cited by this paper
• The Nature of Statistical Learning Theory

  2000cited by this paper
• Modularity in neural computing

  1999cited by this paper
• Classification by Pairwise Coupling

  1997cited by this paper
• Support-Vector Networks

  1995cited by this paper
• A partitioned neural network approach for vowel classification using smoothed time/frequency features

  1993cited by this paper
• Complementary Log Regression for Generalized Linear Models

  1992cited by this paper
• Adaptive Mixtures of Local Experts

  1991cited by this paper

• No citing papers are available for this paper.