Computational creative inferences based on property similarity in a cognitive system


  • proficient in Java 
  • basic knowledge of data structures and algorithms (clustering algorithms and foundations of AI course taken an optional plus)
  • English communication and writing skills - B2
Academic Advisor
Cognitive Systems, Artificial Intelligence, Computational Creativity, Creative Cognition
Master of Science (M.Sc.)


Project context

The Creative Cognitive Systems (CreaCogs) project studies creativity and creative problem solving in natural and artificial cognitive systems -

The aims of this project are twofold. One is the study of creative problem solving in humans. The second is the implementation of, study and experimentation with artificial cognitive systems which yield similar performance as human participants and can be evaluated with human creativity tests. These systems are built on the bases of cognitive knowledge acquisition and cognitively inspired knowledge organization and processes. The Creative Cognitive Systems (CreaCogs) project is supported by the German Research Foundation (DFG).

Problem statement

When humans are missing an object for a task, like a vase to put flowers in, they can make creative inferences about what other objects can be used in the same purpose - for example a cup. In previous work, an object replacement and object composition artificial cognitive system (Olteteanu and Falomir, 2016) which could solve the same type of task has been implemented. This cognitive system was shown to come up with creative uses which are similar to those humans come up with, and to do so via a process similar to the human process, as established by think aloud protocols. 

This system's inferences are based on knowledge of object properties, however its knowledge base at the time was small. To better understand creative inference, an ampler set of object properties data and the deployment of a set of inference algorithms is required. 


More data on object properties is currently being collected from human participants. The scope of this thesis is to use this data and previous cognitive system to computational implement a set of different property based algorithms for creative object replacement. These algorithms will be tested in comparison to human performance, and to well established creativity metrics. 


  • Oltețeanu, Ana-Maria and Falomir, Zoe (2016) - Object Replacement and Object Composition in a Creative Cognitive System. Towards a Computational Solver of the Alternative Uses Test. In Cognitive Systems Research, vol. 39, pp. 15-32. doi:10.1016/j.cogsys.2015.12.011