On the Effectiveness of Interpretable Feedforward Neural Network

TL;DR

This paper introduces a generalized interpretable feedforward neural network (IFFNN) that balances high classification accuracy with interpretability across multiple tasks, demonstrating its practical utility.

Contribution

It extends the IFFNN to multi-class scenarios and various network types, maintaining performance and interpretability, which is novel in the field.

Findings

IFFNN achieves comparable accuracy to standard neural networks.

IFFNN provides meaningful and understandable interpretations.

The generalized IFFNN is effective across different datasets.

Abstract

Deep learning models have achieved state-of-the-art performance in many classification tasks. However, most of them cannot provide an interpretation for their classification results. Machine learning models that are interpretable are usually linear or piecewise linear and yield inferior performance. Non-linear models achieve much better classification performance, but it is hard to interpret their classification results. This may have been changed by an interpretable feedforward neural network (IFFNN) proposed that achieves both high classification performance and interpretability for malware detection. If the IFFNN can perform well in a more flexible and general form for other classification tasks while providing meaningful interpretations, it may be of great interest to the applied machine learning community. In this paper, we propose a way to generalize the interpretable feedforward neural network to multi-class classification scenarios and any type of feedforward neural networks, and evaluate its classification performance and interpretability on intrinsic interpretable datasets. We conclude by finding that the generalized IFFNNs achieve comparable classification performance to their normal feedforward neural network counterparts and provide meaningful interpretations. Thus, this kind of neural network architecture has great practical use.