SpecXAI -- Spectral interpretability of Deep Learning Models

TL;DR

SpecXAI introduces a spectral framework for deep learning interpretability, enabling understanding and transformation of models into linear symbolic forms to enhance explainability in AI systems.

Contribution

The paper presents a novel spectral-based framework, SpecXAI, for interpreting and transforming deep learning models into interpretable symbolic representations.

Findings

Framework effectively characterizes network behavior spectrally

Enables conversion of models into linear interpretable forms

Improves transparency of deep learning models

Abstract

Deep learning is becoming increasingly adopted in business and industry due to its ability to transform large quantities of data into high-performing models. These models, however, are generally regarded as black boxes, which, in spite of their performance, could prevent their use. In this context, the field of eXplainable AI attempts to develop techniques that temper the impenetrable nature of the models and promote a level of understanding of their behavior. Here we present our contribution to XAI methods in the form of a framework that we term SpecXAI, which is based on the spectral characterization of the entire network. We show how this framework can be used to not only understand the network but also manipulate it into a linear interpretable symbolic representation.