GEMS Project

Overview | Publications | Software

Workshop: Computational Scientific Discovery in Social Sciences

2023-05-21

Workshop held on the 12th December 2023 at AI-2023 Forty-third SGAI International Conference on Artificial Intelligence CAMBRIDGE, ENGLAND 12-14 DECEMBER 2023.

http://bcs-sgai.org/ai2023/?section=workshops

This workshop will explore some AI approaches to developing scientific models, particularly considering applications in social science. This area is relatively unexplored, and presents some unique challenges, particularly as models must address both the less-than-perfect accuracy of human behaviour as well as capture this behaviour in time-bound environments. We will provide an introduction and case-studies in this area and deliver a tutorial on GEMS, our own system of scientific discovery.

Chairs: Dr. Peter Lane and Prof. Fernand Gobet. (All enquiries to Peter Lane at <p.c.lane@herts.ac.uk>.)

Programme:

  1. Introduction to Computational Scientific Discovery in Social Sciences, by Prof. Fernand Gobet - slides

  2. Examples of applying this and related methodologies in Psychology and Social Sciences

    1. Evolving Cognitive Models of Verbal Learning, by Dr. Noman Javed and Dr. Dmitry Bennett - slides

    2. Using Genetic Programming to Develop Theories in Psychology, by Dr. Laura Bartlett - slides

  3. Tutorial of the GEMS system, by Dr. Peter Lane - slides

    1. setting up task definitions for scientific experiments

    2. defining a search space of candidate models

    3. searching techniques, such as Genetic Programming.

    4. visualisation and analysis of results

The slides presented in this workshop are licensed under CC BY-NC-ND 4.0