From explainable artificial intelligence to understandable artificial intelligence

Hussein Abbass; Keeley  Crockett; Jonathan  Garibaldi; Alexander Gegov; Uzay Kaymak; Joao Sousa

From explainable artificial intelligence to understandable artificial intelligence

Hussein Abbass^*, Keeley Crockett, Jonathan Garibaldi, Alexander Gegov, Uzay Kaymak, Joao Sousa

^*Corresponding author for this work

Research output: Contribution to journal › Editorial › peer-review

Abstract

We argue that the artificial intelligence (AI) community needs to escape the v of explainable artificial intelligence (xAI) by growing more research on understandable artificial intelligence (uAI). We provocatively term xAI a trap because it has caused some AI researchers to see it as the “end” rather than a “means.” We will discuss why uAI is a better way forward and present a framework for uAI to define research directions that go beyond xAI. Let us first share where this concept emerged before introducing it.

Original language	English
Number of pages	5
Journal	IEEE Transactions on Artificial Intelligence
Publication status	Accepted for publication - 13 Aug 2024

Keywords

Explainable Artificial Intelligence
Understandable Artificial Intelligence
Artificial Intelligence

Cite this

@article{0f6100563b01444c89d9cb6d7198f80f,

title = "From explainable artificial intelligence to understandable artificial intelligence",

abstract = "We argue that the artificial intelligence (AI) community needs to escape the v of explainable artificial intelligence (xAI) by growing more research on understandable artificial intelligence (uAI). We provocatively term xAI a trap because it has caused some AI researchers to see it as the “end” rather than a “means.” We will discuss why uAI is a better way forward and present a framework for uAI to define research directions that go beyond xAI. Let us first share where this concept emerged before introducing it.",

keywords = "Explainable Artificial Intelligence, Understandable Artificial Intelligence, Artificial Intelligence",

author = "Hussein Abbass and Keeley Crockett and Jonathan Garibaldi and Alexander Gegov and Uzay Kaymak and Joao Sousa",

year = "2024",

month = aug,

day = "13",

language = "English",

journal = "IEEE Transactions on Artificial Intelligence",

issn = "2691-4581",

publisher = "IEEE Computational Intelligence Society",

}

TY - JOUR

T1 - From explainable artificial intelligence to understandable artificial intelligence

AU - Abbass, Hussein

AU - Crockett, Keeley

AU - Garibaldi, Jonathan

AU - Gegov, Alexander

AU - Kaymak, Uzay

AU - Sousa, Joao

PY - 2024/8/13

Y1 - 2024/8/13

N2 - We argue that the artificial intelligence (AI) community needs to escape the v of explainable artificial intelligence (xAI) by growing more research on understandable artificial intelligence (uAI). We provocatively term xAI a trap because it has caused some AI researchers to see it as the “end” rather than a “means.” We will discuss why uAI is a better way forward and present a framework for uAI to define research directions that go beyond xAI. Let us first share where this concept emerged before introducing it.

AB - We argue that the artificial intelligence (AI) community needs to escape the v of explainable artificial intelligence (xAI) by growing more research on understandable artificial intelligence (uAI). We provocatively term xAI a trap because it has caused some AI researchers to see it as the “end” rather than a “means.” We will discuss why uAI is a better way forward and present a framework for uAI to define research directions that go beyond xAI. Let us first share where this concept emerged before introducing it.

KW - Explainable Artificial Intelligence

KW - Understandable Artificial Intelligence

KW - Artificial Intelligence

UR - https://cis.ieee.org/publications/ieee-transactions-on-artificial-intelligence

M3 - Editorial

SN - 2691-4581

JO - IEEE Transactions on Artificial Intelligence

JF - IEEE Transactions on Artificial Intelligence

ER -