A Categorisation of Post-hoc Explanations for Predictive Models

Files in This Item:
File Description SizeFormat 
insight_publication.pdf281.01 kBAdobe PDFDownload
Title: A Categorisation of Post-hoc Explanations for Predictive Models
Authors: Mitros, John (Ioannis)MacNamee, Brian
Permanent link: http://hdl.handle.net/10197/12202
Date: 27-Mar-2019
Online since: 2021-05-26T10:33:57Z
Abstract: The ubiquity of machine learning based predictive models inmodern society naturally leads people to ask how trustworthythose models are? In predictive modeling, it is quite commonto induce a trade-off between accuracy and interpretability.For instance, doctors would like to know how effective sometreatment will be for a patient or why the model suggesteda particular medication for a patient exhibiting those symptoms? We acknowledge that the necessity for interpretabilityis a consequence of an incomplete formalisation of the prob-lem, or more precisely of multiple meanings adhered to a par-ticular concept. For certain problems, it is not enough to getthe answer (what), the model also has to provide an expla-nation of how it came to that conclusion (why), because acorrect prediction, only partially solves the original problem.In this article we extend existing categorisation of techniquesto aid model interpretability and test this categorisation
Funding Details: Science Foundation Ireland
Funding Details: Insight Research Centre
Type of material: Conference Publication
Publisher: Association for the Advancement of Artificial Intelligence
Copyright (published version): 2018 Association for the Advancement of Artificial Intelligence
Keywords: Machine learning & statisticsInterpretability
Other versions: https://aaai.org/Symposia/Spring/sss19.php
Language: en
Status of Item: Peer reviewed
Conference Details: The 2019 Association for the Advancement of Artificial Intelligence (AAAI) Spring Symposia on Combining Machine Learning with Knowledge Engineering (AAAI-MAKE 2019), Palo Alto, California, 25-27 March 2019
This item is made available under a Creative Commons License: https://creativecommons.org/licenses/by-nc-nd/3.0/ie/
Appears in Collections:Computer Science Research Collection
Insight Research Collection

Show full item record

Page view(s)

20
Last Week
3
Last month
checked on Jun 15, 2021

Download(s)

5
checked on Jun 15, 2021

Google ScholarTM

Check


If you are a publisher or author and have copyright concerns for any item, please email research.repository@ucd.ie and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.