Trainable and Explainable Simplicial Map Neural Networks

Abstract

Simplicial map neural networks (SMNNs) are topology-based neural networks with interesting properties such as universal approximation ability and robustness to adversarial examples under appropriate conditions. However, SMNNs present some bottlenecks for their possible application in high-dimensional datasets. First, SMNNs have precomputed fixed weight and no SMNN training process has been defined so far, so they lack generalization ability. Second, SMNNs require the construction of a convex polytope surrounding the input dataset. In this paper, we overcome these issues by proposing an SMNN training procedure based on a support subset of the given dataset and replacing the construction of the convex polytope by a method based on projections to a hypersphere. In addition, the explainability capacity of SMNNs and an effective implementation are also newly introduced in this paper.

References in corpus (5)

• Scikit-learn: Machine Learning in Python
• Interpretable machine learning: definitions, methods, and applications
• On the approximation by single hidden layer feedforward neural networks with fixed weights
• Two-hidden-layer Feedforward Neural Networks are Universal Approximators: A Constructive Approach
• Topology-based Representative Datasets to Reduce Neural Network Training Resources