Predicting Numbers: An AI Approach to Solving Number Series

Ragni, Marco

doi:10.1007/978-3-642-24455-1_24

Cited by 19 publications

(29 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Ragni and Klein [121] worked on number series completion, which is very common in many intelligence tests and also occasionally in artificial intelligence [136]. They took over 50,000 number series from the Online Encyclopedia of Integer Sequences (OEIS) and applied a general method using artificial neural networks (ANNs) and dynamic learning.…”

Section: -10mentioning

confidence: 99%

“…In particular, Ragni and Neubert use five: constant in a row, distribution of three values, quantitative pairwise progression, figure addition, and distribution of two values. Unlike the previous work [121], the motivation of this work is to solve the problems in a cognitive way, i.e., explaining why the system fails (ambiguousness, objects neglected, incorrect rules applied, . .…”

Section: -10mentioning

confidence: 99%

“…Siebers and Schmid [128] address the number series problem with a cognitive model, differently to other previous approaches for the same problem introduced before [121,136]. They use their own (public) series collection formed by 25,000 randomly created number series (using the basic numerical operators), for which the accuracy was 93.2%.…”

Section: -10mentioning

confidence: 99%

“…Finally, note that those systems addressing word, letter, or number-based tasks are able to use raw "strings" or number/letter sequences directly [11,96,15,121,128,131,132], meanwhile others need specific types for input problems: Hofmann, Kitzelmann, and Schmid's system [135] needs algebraic data-types for the target function together with a small set of examples; Ragni and Klein's system [121] and Siebers and Schmid's system [128] need to transform the sequences into different train and test sets.…”

Section: Input Representation Techniquesmentioning

confidence: 99%

See 3 more Smart Citations

Computer models solving intelligence test problems: Progress and implications

Hernández-Orallo

Martínez-Plumed

Schmid

et al. 2016

Artificial Intelligence

View full text Add to dashboard Cite

ElsevierHernández Orallo, J.; Martínez Plumed, F.; Schmid, U.; Siebers, M.; Dowe, DL. (2016 AbstractWhile some computational models of intelligence test problems were proposed throughout the second half of the XXth century, in the first years of the XXIst century we have seen an increasing number of computer systems being able to score well on particular intelligence test tasks. However, despite this increasing trend there has been no general account of all these works in terms of how they relate to each other and what their real achievements are. Also, there is poor understanding about what intelligence 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. In this paper, we provide some insight on these issues, in the form of nine specific questions, by giving a comprehensive account of about thirty computer models, from the 1960s to nowadays, and their relationships, focussing on the range of intelligence test tasks they address, the purpose of the models, how general or specialised these models are, the AI techniques they use in each case, their comparison with human performance, and their evaluation of item difficulty. As a conclusion, these tests and the computer models attempting them show that AI is still lacking general techniques to deal with a variety of problems at the same time. Nonetheless, a renewed attention on these problems and a more careful understanding of what intelligence tests offer for AI may help build new bridges between psychometrics, cognitive science, and AI; and may motivate new kinds of problem repositories.

show abstract

Section: -10mentioning

confidence: 99%

Section: -10mentioning

confidence: 99%

Section: -10mentioning

confidence: 99%

Section: Input Representation Techniquesmentioning

confidence: 99%

See 2 more Smart Citations

Computer models solving intelligence test problems: Progress and implications

Hernández-Orallo

Martínez-Plumed

Schmid

et al. 2016

Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Closely related to the approach of Turney we find the work of Bayoudh et al [2012]. Ragni and Klein [2011] worked on number series completion applying a general machine learning method. Ragni and Neubert [2014] presented a system for Raven's Progressive Matrices which motivation is to solve the problems in a cognitive way, i.e., explaining why the system fails.…”

Section: Historical Accountmentioning

confidence: 78%

Computer Models Solving Intelligence Test Problems: Progress and Implications (Extended Abstract)

Hernández-Orallo

Martínez-Plumed

Schmid

et al. 2017

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

While some computational models of intelligence test problems were proposed throughout the second half of the XXth century, in the first years of the XXIst century we have seen an increasing number of computer systems being able to score well on particular intelligence test tasks. However, despite this increasing trend there has been no general account of all these works in terms of how they relate to each other and what their real achievements are. In this paper, we provide some insight on these issues by giving a comprehensive account of about thirty computer models, from the 1960s to nowadays, and their relationships, focussing on the range of intelligence test tasks they address, the purpose of the models, how general or specialised these models are, the AI techniques they use in each case, their comparison with human performance, and their evaluation of item difficulty.

show abstract

Deriving Formulas for Integer Sequences Using Inductive Programming

Ridder

Vercammen

2019

Communications in Computer and Information Science

View full text Add to dashboard Cite

Predicting Numbers: An AI Approach to Solving Number Series

Cited by 19 publications

References 1 publication

Computer models solving intelligence test problems: Progress and implications

Computer models solving intelligence test problems: Progress and implications

Computer Models Solving Intelligence Test Problems: Progress and Implications (Extended Abstract)

Deriving Formulas for Integer Sequences Using Inductive Programming

Contact Info

Product

Resources

About