LGAIJul 1, 2023

Interpretable Neural Networks with Random Constructive Algorithm

arXiv:2307.00185v31 citationsh-index: 15
Originality Incremental advance
AI Analysis

This addresses the problem of interpretability in neural networks for researchers and practitioners, but it appears incremental as it builds on existing random weighted neural networks with added interpretability features.

The paper tackles the opaque parameterization of random weighted neural networks by introducing an Interpretable Neural Network (INN) that uses spatial information and geometric strategies to improve interpretability and convergence, achieving superior modeling speed, accuracy, and structure on benchmark datasets and real-world cases.

This paper introduces an Interpretable Neural Network (INN) incorporating spatial information to tackle the opaque parameterization process of random weighted neural networks. The INN leverages spatial information to elucidate the connection between parameters and network residuals. Furthermore, it devises a geometric relationship strategy using a pool of candidate nodes and established relationships to select node parameters conducive to network convergence. Additionally, a lightweight version of INN tailored for large-scale data modeling tasks is proposed. The paper also showcases the infinite approximation property of INN. Experimental findings on various benchmark datasets and real-world industrial cases demonstrate INN's superiority over other neural networks of the same type in terms of modeling speed, accuracy, and network structure.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes