• Corpus ID: 16800819

Using Human Computation to Acquire Novel Methods for Addressing Visual Analogy Problems on Intelligence Tests

  title={Using Human Computation to Acquire Novel Methods for Addressing Visual Analogy Problems on Intelligence Tests},
  author={David A. Joyner and Darren Bedwell and Chris Graham and Warren Lemmon and {\'O}scar Mart{\'i}nez and Ashok K. Goel},
The Raven's Progressive Matrices (RPM) test is a commonly used test of intelligence. The literature suggests a variety of problem-solving methods for addressing RPM problems. For a graduate-level artificial intelligence class in Fall 2014, we asked students to develop intelligent agents that could address 123 RPM-inspired problems, essentially crowdsourcing RPM problem solving. The students in the class submitted 224 agents that used a wide variety of problem-solving methods. In this paper, we… 

Figures and Tables from this paper

Using AI to Teach AI: Lessons from an Online AI Class
The design, delivery, and evaluation of the course, focusing on the use of AI for teaching AI, are presented, and lessons learned for scaling the teaching and learning of AI are discussed.
Artificial Cognitive Systems That Can Answer Human Creativity Tests: An Approach and Two Case Studies
An approach is proposed for building cognitive systems which can solve human creativity tests, and the applicability of this general approach to other creativity tests and artificial cognitive systems, together with ways of performing cognitive knowledge acquisition for these systems are explored.
An Experiment in Teaching Cognitive Systems Online
The design, development and delivery of the online KBAI class are described, and comparison of their performance with the students in the inperson class suggests that the online course appears to have been a success.
Regent-Dependent Creativity: A Domain Independent Metric for the Assessment of Creative Artifacts
This paper proposes an domain independent metric, called Regent-Dependent Creativity (RDC), that assesses the creativity of artifacts, and combines the Bayesian Surprise and Synergy to measure novelty and value.
TwitSong: A current events computer poet and the thorny problem of assessment.
While TwitSong does not turn out to produce poetry comparable to that of a human, it represents an advancement on the state of the art in its genre of computer-generated poetry, particularly in its ability to edit for qualities like topicality and emotion.
Creative Flavor Pairing: Using RDC Metric to Generate and Assess Ingredients Combination
Creating culinary recipes is one of the most creative human activities. It requires combining ingredients, performing the recipe steps, creating specific diets, and others tasks. In addition to it,
Evaluating Computational Creativity
This article is a tutorial for researchers who are designing software to perform a creative task and want to evaluate their system using interdisciplinary theories of creativity. Researchers who
Design of an Online Course on Knowledge-Based AI
The design, development and delivery of the online KBAI class in Fall 2014 is described, which offered an online course on Knowledge-Based Artificial Intelligence to about 200 students as part of the Georgia Tech Online MS in CS program.
Five Years of Graduate CS Education Online and at Scale
A unique and powerful unity of content and platform is noted: the online delivery of the program dovetails with the technical skillsets of the professors and students that it draws, putting both in the position to contribute and innovate.


Analyzing Raven's Intelligence Test: Cognitive Model, Demand, and Complexity
It is argued that in addition to visual and formal reasoning difficulty the way information is processed in the modular structure of the human mind should be taken into account.
Solving Geometric Analogy Problems Through Two-Stage Analogical Mapping
It is demonstrated that the structure mapping model of analogy, when combined with high-level visual processing and qualitative representations, can solve the same kinds of geometric analogy problems as were solved by ANALOGY.
Analogy-Making for Solving IQ Tests: A Logical View
This paper shows how a Boolean logic view of analogical proportions can be the basis of a simple inference paradigm that provides a rigorous way to solve representative analogy-based IQ tests by computing the missing items rather than by choosing in a list of options.
Effects of strategy training on Progressive Matrices performance
Learning about representational modality: design and programming projects for knowledge-based AI
An investigation into learning about representational modality through a series of projects based around geometric analogy problems similar to the Raven's Progressive Matrices test of intelligence, which discovered that students found these projects motivating, engaging, and challenging.
Methods for Classifying Errors on the Raven's Standard Progressive Matrices Test
A preliminary analysis of error patterns on the SPM from typically developing individuals, individuals diagnosed with autism, and a computational model called ASTI is presented, discussing what the error patterns suggest regarding cognition on theSPM and routes towards improving the ASTI model.
Human computation
This talk discusses a paradigm for utilizing human processing power to solve problems that computers cannot yet solve, and advocates a novel approach: constructively channel human brainpower using computer games.
A program for the solution of a class of geometric-analogy intelligence-test questions
13,072. Brandenberger, J. E. May 31. 1913, [Convention date]. Compound fabrics and sheet materials.-Films for photographic and like purposes consist of two previously prepared outer films of
Spatial Cognition of Geometric Figures in the Context of Proportional Analogies
This work investigated experimentally how humans perceive geometric figures in geometric proportional analogies and discovered that subjects perceive structures within the figures which are suitable for solving the analogy.