Historical account of computer models solving IQ test problems

Fernando Martínez-Plumed; Jose Hernandez-Orallo; Ute Schmid; Michael Siebers; David L. Dowe

Historical account of computer models solving IQ test problems

Fernando Martínez-Plumed
, Jose Hernandez-Orallo
, Ute Schmid
, Michael Siebers
, David L. Dowe

Department of Data Science & AI

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Other

Abstract

In this short paper we summarise our work in [9] where
we make a review of what has been done when intelligence test problems have been analysed through cognitive models or particular systems. This work has been motivated by an observed explosion of the number of papers on this topic in recent years. We have made a general account of all these works in terms of how they relate to each other and what their real achievements are. Not only do we aim at analysing the meaning, utility, and impact of these computer models, but also better understanding what these tests measure in machines, whether they are useful to evaluate AI systems, whether they are really challenging problems, and whether they are useful to understand (human) intelligence.

Original language	English
Title of host publication	EGPAI 2016 - Evaluating General Purpose AI 2016
Editors	Christos Dimitrakakis, Jose Hernandez-Orallo, Claes Strannegard, Kristinn R. Thorisson
Place of Publication	Palo Alto CA USA
Publisher	Association for the Advancement of Artificial Intelligence (AAAI)
Number of pages	2
Publication status	Published - 2016
Event	Evaluating General Purpose AI 2016 - The Hague, Netherlands Duration: 30 Aug 2016 → 30 Aug 2016 http://dmip.webs.upv.es/EGPAI2016/

Conference

Conference	Evaluating General Purpose AI 2016
Abbreviated title	EGPAI 2016
Country/Territory	Netherlands
City	The Hague
Period	30/08/16 → 30/08/16
Internet address	http://dmip.webs.upv.es/EGPAI2016/

Access to Document

376161575-oaFinal published version, 86.2 KB

http://chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/viewer.html?pdfurl=http%3A%2F%2Fdmip.webs.upv.es%2FEGPAI2016%2Fpapers%2FEGPAI_2016_paper_5.pdf&clen=93326&chunk=true

Cite this

Martínez-Plumed, F., Hernandez-Orallo, J., Schmid, U., Siebers, M., & L. Dowe, D. (2016). Historical account of computer models solving IQ test problems. In C. Dimitrakakis, J. Hernandez-Orallo, C. Strannegard, & K. R. Thorisson (Eds.), EGPAI 2016 - Evaluating General Purpose AI 2016 Association for the Advancement of Artificial Intelligence (AAAI). http://chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/viewer.html?pdfurl=http%3A%2F%2Fdmip.webs.upv.es%2FEGPAI2016%2Fpapers%2FEGPAI_2016_paper_5.pdf&clen=93326&chunk=true

Martínez-Plumed, Fernando ; Hernandez-Orallo, Jose ; Schmid, Ute et al. / Historical account of computer models solving IQ test problems. EGPAI 2016 - Evaluating General Purpose AI 2016. editor / Christos Dimitrakakis ; Jose Hernandez-Orallo ; Claes Strannegard ; Kristinn R. Thorisson. Palo Alto CA USA : Association for the Advancement of Artificial Intelligence (AAAI), 2016.

@inproceedings{70d263a1694c44858b7a1a6caed266ed,

title = "Historical account of computer models solving IQ test problems",

abstract = "In this short paper we summarise our work in [9] where we make a review of what has been done when intelligence test problems have been analysed through cognitive models or particular systems. This work has been motivated by an observed explosion of the number of papers on this topic in recent years. We have made a general account of all these works in terms of how they relate to each other and what their real achievements are. Not only do we aim at analysing the meaning, utility, and impact of these computer models, but also better understanding what these tests measure in machines, whether they are useful to evaluate AI systems, whether they are really challenging problems, and whether they are useful to understand (human) intelligence.",

author = "Fernando Mart{\'i}nez-Plumed and Jose Hernandez-Orallo and Ute Schmid and Michael Siebers and \{L. Dowe\}, David",

year = "2016",

language = "English",

editor = "Christos Dimitrakakis and Jose Hernandez-Orallo and Claes Strannegard and \{R. Thorisson\}, Kristinn",

booktitle = "EGPAI 2016 - Evaluating General Purpose AI 2016",

publisher = "Association for the Advancement of Artificial Intelligence (AAAI)",

address = "United States of America",

note = "Evaluating General Purpose AI 2016, EGPAI 2016 ; Conference date: 30-08-2016 Through 30-08-2016",

url = "http://dmip.webs.upv.es/EGPAI2016/",

}

Martínez-Plumed, F, Hernandez-Orallo, J, Schmid, U, Siebers, M & L. Dowe, D 2016, Historical account of computer models solving IQ test problems. in C Dimitrakakis, J Hernandez-Orallo, C Strannegard & K R. Thorisson (eds), EGPAI 2016 - Evaluating General Purpose AI 2016. Association for the Advancement of Artificial Intelligence (AAAI), Palo Alto CA USA, Evaluating General Purpose AI 2016, The Hague, Netherlands, 30/08/16. <http://chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/viewer.html?pdfurl=http%3A%2F%2Fdmip.webs.upv.es%2FEGPAI2016%2Fpapers%2FEGPAI_2016_paper_5.pdf&clen=93326&chunk=true>

Historical account of computer models solving IQ test problems. / Martínez-Plumed, Fernando; Hernandez-Orallo, Jose; Schmid, Ute et al.
EGPAI 2016 - Evaluating General Purpose AI 2016. ed. / Christos Dimitrakakis; Jose Hernandez-Orallo; Claes Strannegard; Kristinn R. Thorisson. Palo Alto CA USA: Association for the Advancement of Artificial Intelligence (AAAI), 2016.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Other

TY - GEN

T1 - Historical account of computer models solving IQ test problems

AU - Martínez-Plumed, Fernando

AU - Hernandez-Orallo, Jose

AU - Schmid, Ute

AU - Siebers, Michael

AU - L. Dowe, David

PY - 2016

Y1 - 2016

N2 - In this short paper we summarise our work in [9] where we make a review of what has been done when intelligence test problems have been analysed through cognitive models or particular systems. This work has been motivated by an observed explosion of the number of papers on this topic in recent years. We have made a general account of all these works in terms of how they relate to each other and what their real achievements are. Not only do we aim at analysing the meaning, utility, and impact of these computer models, but also better understanding what these tests measure in machines, whether they are useful to evaluate AI systems, whether they are really challenging problems, and whether they are useful to understand (human) intelligence.

AB - In this short paper we summarise our work in [9] where we make a review of what has been done when intelligence test problems have been analysed through cognitive models or particular systems. This work has been motivated by an observed explosion of the number of papers on this topic in recent years. We have made a general account of all these works in terms of how they relate to each other and what their real achievements are. Not only do we aim at analysing the meaning, utility, and impact of these computer models, but also better understanding what these tests measure in machines, whether they are useful to evaluate AI systems, whether they are really challenging problems, and whether they are useful to understand (human) intelligence.

M3 - Conference Paper

BT - EGPAI 2016 - Evaluating General Purpose AI 2016

A2 - Dimitrakakis, Christos

A2 - Hernandez-Orallo, Jose

A2 - Strannegard, Claes

A2 - R. Thorisson, Kristinn

PB - Association for the Advancement of Artificial Intelligence (AAAI)

CY - Palo Alto CA USA

T2 - Evaluating General Purpose AI 2016

Y2 - 30 August 2016 through 30 August 2016

ER -