More than one kind of inference: Re-examining what's learned in feature inference and classification

Abstract

Three studies examined how task demands that impact on attention to typical or atypical category features shape the category representations formed through classification learning and inference learning. During training categories were learned via exemplar classification or by inferring missing exemplar features. In the latter condition inferences were made about missing typical features alone (typical feature inference) or about both missing typical and atypical features (mixed feature inference). Classification and mixed feature inference led to the incorporation of typical and atypical features into category representations, with both kinds of features influencing inferences about familiar (Experiments 1 and 2) and novel (Experiment 3) test items. Those in the typical inference condition focused primarily on typical features. Together with formal modelling, these results challenge previous accounts that have characterized inference learning as producing a focus on typical category features. The results show that two different kinds of inference learning are possible and that these are subserved by different kinds of category representations.

Keywords:

• Categorisation
• Category learning
• Inference learning
• Induction

Acknowledgments

Naomi Sweller is now at the Children and Families Research Centre, Institute of Early Childhood, Macquarie University, Sydney, NSW 2109, Australia. This work was supported by an Australian Postgraduate Award to the first author and an Australian Research Council Discovery Grant to the second author.

Notes

¹ The greater number of features present in each stimulus in Experiment 3 resulted in a larger number of inference questions being possible for each item than in Experiments 1 and 2.

² Experiment 3 data were not fitted because of the complexity of observed patterns of test performance. Preliminary model fitting suggested that because of high standard deviations around the mean classification and inference responses for medium similarity items none of the target models would produce a good fit.