You are here: Home Teaching Predicting Cognition via Machine …

Predicting Cognition via Machine Learning (WS 2018)

Organizer: Marco Ragni
Assistants: Nicolas RiestererLukas Elflein


Traditionally, cognitive science aimed at connecting experimental psychological research with computational modelling techniques typical for computer science and artificial intelligence (AI). In this seminar, we make an attempt at tying both research fields even closer together. By defining a prediction setting, the goal is to develop modern models capable of forecasting human responses to reasoning tasks based on concepts inspired by machine learning and AI. In particular, seminar participants will be given the chance to extend existing approaches or develop new accounts on their own.

Theoretical Background

  • Khemlani, S., & Johnson-Laird, P. N. (2012). Theories of the syllogism: A meta-analysis. Psychological bulletin138(3), 427.
  • Hattori, M. (2016). Probabilistic representation in syllogistic reasoning: A theory to integrate mental models and heuristics. Cognition157, 296-320.
  • da Costa, A. O., Saldanha, E. A. D., Hölldobler, S., & Ragni, M. (2017). A computational logic approach to human syllogistic reasoning. In Proceedings of the 39th Annual Conference of the Cognitive Science Society.
  • Riesterer N., Brand D., Ragni M. (2018) The Predictive Power of Heuristic Portfolios in Human Syllogistic Reasoning. In: Trollmann F., Turhan AY. (Eds.) KI 2018: Advances in Artificial Intelligence. KI 2018. Lecture Notes in Computer Science, vol 11117. Springer, Cham.

Important Dates & Deadlines

  • Oct 15th, 2018, 12:00-14:00, building 52, room 02-017: Introductory Meeting [slides]
  • Oct 24th, 2018: Registration Deadline (via HisInOne)
  • Oct 30th, 2018, 14:00-16:00, building 101, room 01-016: Setup Meeting (Framework installation, demo model implementation) [slides][examples]
  • Dec 2nd, 2018, 23:59: Deadline submission preliminary models
  • Dec 3rd, 2018, 12:00-14:00, building 106, room 00-007: Midterm presentation of preliminary results
  • Jan 13th, 2019, 23:59: Deadline for the written report
  • Jan 19th-20th, 2019, 09:00, building 51, room 03-026: Blockseminary


  • Conceptualization, analysis and implementation of a model for syllogistic reasoning in the CCOBRA framework
  • Presentation of your preliminary & final results
    • Theoretical and computational foundation
    • Simulation performance
    • Ideas for improvement
  • Written report of your work (~6 pages, CogSci Layout)
    • Introduction/Motivation
    • Theoretical Foundation
    • Method/Model
    • Results
    • Conclusions/Discussion