Recursive functions of symbolic expressions and their computation by machine, Part I
Communications of the ACM
LISP 1.5 Programmer's Manual
Sketchpad: a man-machine graphical communication system
AFIPS '63 (Spring) Proceedings of the May 21-23, 1963, spring joint computer conference
CYCLOPS-1: a second-generation recognition system
AFIPS '63 (Fall) Proceedings of the November 12-14, 1963, fall joint computer conference
Linguistic methods in picture processing: a survey
AFIPS '68 (Fall, part I) Proceedings of the December 9-11, 1968, fall joint computer conference, part I
The latent relation mapping engine: algorithm and experiments
Journal of Artificial Intelligence Research
Machine perception and description of pictorial data
IJCAI'69 Proceedings of the 1st international joint conference on Artificial intelligence
Analogy-Making for solving IQ tests: a logical view
ICCBR'11 Proceedings of the 19th international conference on Case-Based Reasoning Research and Development
Complex analogies: remarks on the complexity of HDTP
AI'12 Proceedings of the 25th Australasian joint conference on Advances in Artificial Intelligence
How universal can an intelligence test be?
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
| Hi-index | 0.00 |
The purpose of this paper is to describe a program now in existence which is capable of solving a wide class of the so-called 'geometric-analogy' problems frequently encountered on intelligence tests. Each member of this class of problems consists of a set of labeled line drawings. The task to be performed can be concisely described by the question: 'figure A is to figure B as figure C is to which of the given answer figures?' For example, given the problem illustrated as Fig. 1, the geometric-analogy program (which we shall subsequently call ANALOGY, for brevity) selected the problem figure labeled 4 as its answer. It seems safe to say that most people would agree with ANALOGY's answer to this problem (which, incidentally, is taken from the 1942 edition of the Psychological Test for College Freshmen of the American Council on Education). Furthermore, if one were required to make explicit the reasoning by which he arrived at his answer, prospects are good that the results would correspond closely to the description of its 'reasoning' produced by ANALOGY.