Balancing Explainability-Accuracy of Complex Models

05/23/2023
by   Poushali Sengupta, et al.
UNIVERSITETET I OSLO
0

Explainability of AI models is an important topic that can have a significant impact in all domains and applications from autonomous driving to healthcare. The existing approaches to explainable AI (XAI) are mainly limited to simple machine learning algorithms, and the research regarding the explainability-accuracy tradeoff is still in its infancy especially when we are concerned about complex machine learning techniques like neural networks and deep learning (DL). In this work, we introduce a new approach for complex models based on the co-relation impact which enhances the explainability considerably while also ensuring the accuracy at a high level. We propose approaches for both scenarios of independent features and dependent features. In addition, we study the uncertainty associated with features and output. Furthermore, we provide an upper bound of the computation complexity of our proposed approach for the dependent features. The complexity bound depends on the order of logarithmic of the number of observations which provides a reliable result considering the higher dimension of dependent feature space with a smaller number of observations.

READ FULL TEXT

page 1

page 2

page 3

page 4

03/24/2023

Derivative-based Shapley value for global sensitivity analysis and machine learning explainability

We introduce a new Shapley value approach for global sensitivity analysi...
05/20/2023

A Survey of Explainable AI and Proposal for a Discipline of Explanation Engineering

In this survey paper, we deep dive into the field of Explainable Artific...
01/13/2021

Explainability of vision-based autonomous driving systems: Review and challenges

This survey reviews explainability methods for vision-based self-driving...
11/19/2021

ExoMiner: A Highly Accurate and Explainable Deep Learning Classifier to Mine Exoplanets

The kepler and TESS missions have generated over 100,000 potential trans...
06/05/2023

From Robustness to Explainability and Back Again

In contrast with ad-hoc methods for eXplainable Artificial Intelligence ...

Please sign up or login with your details

Forgot password? Click here to reset