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

Aus de_evolutionary_art_org
Wechseln zu: Navigation, Suche


David Joyner, Darren Bedwell, Chris Graham, Warren Lemmon, Oscar Martinez and Ashok K. Goel: Using Human Computation to Acquire Novel Methods for Addressing Visual Analogy Problems on Intelligence Tests. In: Computational Creativity 2015 ICCC 2015, 23-30.



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 first report on the aggregate results of those 224 agents on the 123 problems, then focus specifically on four of the most creative, novel, and effective agents in the class. We find that the four agents, using four very different problem-solving methods, were all able to achieve significant success. This suggests the RPM test may be amenable to a wider range of problem- solving methods than previously reported. It also suggests that human computation might be an effective strategy for collecting a wide variety of methods for creative tasks.

Extended Abstract


 author = {Joyner, David and Bedwell, Darren and Graham, Chris and Lemmon, Warren and Martinez, Oscar and Goel, Ashok K.},
 title = {Using Human Computation to Acquire Novel Methods for Addressing Visual Analogy Problems on Intelligence Tests},
 booktitle = {Proceedings of the Sixth International Conference on Computational Creativity},
 series = {ICCC2015},
 year = {2015},
 month = {Jun},
 location = {Park City, Utah, USA},
 pages = {23-30},
 url = { },
 publisher = {International Association for Computational Creativity},
 keywords = {computational, creativity},

Used References

Bringsjord, S., & Schimanski, B. (2003). What is Artificial Intelligence? Psychometric AI as an answer. In Procs. 18th IJCAI, 887-893.

Dastani, M., Indurkhya, B., & Scha, R. (2003). Analogical Perception in Pattern Completion. JETAI 15(4), 489-511.

Evans, T. (1967). A Program for the Solution of a Class of Geometric Analogy Intelligence-Test Questions. In M. Minsky (ed.) Semantic Information Processing. MIT Press. Goel, A. & Joyner, D. (2014). CS7637: Knowledge-Based AI: Cognitive Systems [Online Course]. Retrieved from

Goel, A. & Joyner, D. (2015). An Experiment in Teaching Cognitive Systems Online. Technical Report, Georgia Institute of Technology.

Goel, A., Kunda, M., Joyner, D., & Vattam, S. (2013). Learning about Representational Modality: Design and Programming Projects for Knowledge-Based AI. In Fourth AAAI Symposium on Educational Advances in Artificial Intelligence.

Howe, J. (2008). Crowdsourcing: Why the Power of the Crowd is Driving the Future of Business. Crown.

Hunt, E. (1974). Quote the raven? Nevermore! In L. W. Gregg (Ed.), Knowledge and Cognition. 129-158. Hillsdale, NJ: Erlbaum.

Keating, D. , & Bobbitt, B. (1978). Individual and developmental differences in cognitive-processing components of mental ability. Child Development, 155-167.

Kirby, J., & Lawson, M. (1983). Effects of strategy training on progressive matrices performance. Contemporary Educational Psychology, 8(2), 127-140.

Kunda, M., & Goel, A. (2011). Thinking in Pictures as a Cognitive Account of Autism. Journal of Autism and Developmental Disorders, 41(9), 1157-1177.

Kunda, M., McGreggor, K., & Goel, A. (2013). A Computational Model for Solving Problems from the Raven’s Progressive Matrices Intelligence test using Iconic Visual Representations. Cognitive Systems Research, 22, 47-66. Kunda, M., Soulieres, I., Rozga, A., & Goel, A. (2013).

Methods for Classifying Errors on the Raven's Standard Progressive Matrices Test. In Proceedings of the 35th Annual Meeting of the Cognitive Science Society, 2796-2801. Berlin, Germany.

Law, E., & von Ahn, L. (2011). Human Computation. Morgan & Claypool.

Lovett, A., Tomai, E., Forbus, K. & Usher, J. (2009). Solving geometric analogy problems through two-stage analogical mapping. Cognitive Science 33(7), 1192-1231.

Lynn, R., Allik, J., & Irwing, P. (2004). Sex differences on three factors identified in Raven's SPM. Intelligence, 32, 411-424. McGreggor, K., Kunda, M., & Goel, A. (2014). Fractal and Ravens. Artificial Intelligence 215, 1-23. O’Donoghue, D., Bohan, A., & Keane, M. (2006). Seeing Things: Inventive Reasoning with Geometric Analogies and Topographic Maps. New Generation Computing 24 (3), 267-288.

Prade, H. & Richard, G. (2011). Analogy-Making for Solving IQ Tests: A Logical View. In Procs. 19th International Conference on Case-Based Reasoning, 561-566. London, UK: Springer.

Ragni, M. & Neubert, S. (2014). Analyzing Raven’s Intelligence Test: Cognitive Model, Demand, and Complexity. In H. Prade & G. Richard (Eds.) Computational Approaches to Analogical Reasoning: Current Trends, 351-370. Springer.

Raven, J., Raven, J. C., & Court, J. (1998). Manual for Raven's Progressive Matrices and Vocabulary Scales. San Antonio, TX: Harcourt Assessment.

Schwering, A., Krumnack, U., Kuhnberger, K-U, & Gust, H. (2009). Spatial cognition of geometric figures in the context of proportional analogies. In Procs. Spatial Information Theory, Lecture Notes in Computer Science Volume 5756, 18-35.

Snow, R., Kyllonen, P., & Marshalek, B. (1984). The topography of ability and learning correlations. Advances in the Psychology of Human Intelligence, 2, 47-103.


Full Text

intern file

Sonstige Links