Proceedings of the Annual Meeting of the Cognitive Science Society

A key aspect of human reasoning is the ability to recognize abstract patterns in sequential data and then use those patternsto make novel inferences. Capturing this capacity for abstract reasoning is a major challenge for neural network modelsof human cognition. We present a recurrent neural network model of abstract sequential reasoning that is augmented witha form of episodic memory. This memory system enables the network to accomplish a form of variable-binding that haslong been considered an important component of abstract reasoning. We evaluate the model using visually grounded,abstract sequential reasoning and pattern completion tasks, including a task based on relations commonly found in RavensProgressive Matrices.