Explainable artificial intelligence (XAI), the goodness criteria and the grasp-ability test

10/22/2018
by   Tae Wan Kim, et al.
0

This paper introduces the "grasp-ability test" as a "goodness" criteria by which to compare which explanation is more or less meaningful than others for users to understand the automated algorithmic data processing.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/25/2023

An Experimental Investigation into the Evaluation of Explainability Methods

EXplainable Artificial Intelligence (XAI) aims to help users to grasp th...
research
06/21/2018

Towards a Grounded Dialog Model for Explainable Artificial Intelligence

To generate trust with their users, Explainable Artificial Intelligence ...
research
09/12/2023

On the Injunction of XAIxArt

The position paper highlights the range of concerns that are engulfed in...
research
02/18/2022

Sample Efficient Grasp Learning Using Equivariant Models

In planar grasp detection, the goal is to learn a function from an image...
research
07/25/2019

Validating and Updating GRASP: A New Evidence-Based Framework for Grading and Assessment of Clinical Predictive Tools

Background: When selecting predictive tools, for implementation in clini...
research
03/03/2020

EXPLAIN-IT: Towards Explainable AI for Unsupervised Network Traffic Analysis

The application of unsupervised learning approaches, and in particular o...
research
07/20/2020

Artificial Intelligence is stupid and causal reasoning won't fix it

Artificial Neural Networks have reached Grandmaster and even super-human...

Please sign up or login with your details

Forgot password? Click here to reset