Jin Huang¹ (), Deeksha Arun¹, Terrance Boult², Walter Scheirer¹; ¹Department of Computer Science and Engineering, University of Notre Dame, ²Department of Computer Science, University of Colorado, Colorado Springs

Several possibilities exist for modeling decision boundaries in category learning, with varying degrees of human fidelity. This paper finds evidence for preferentially focusing representational resources on the extremes of the distribution of visual inputs in a generative model as an alternative to the central tendency models that are commonly used for prototypes and exemplars. The notion of treating extrema near a decision boundary as features in visual recognition is not new, but a comprehensive statistical framework of recognition based on extrema has yet to emerge for category learning. Here we suggest that the statistical Extreme Value Theory provides such a framework. In Experiment 1, vertical line stimuli that vary in a single dimension of length are used to assess how human subjects and statistical models assign category membership to a gap region between two categories previously shown as training data. A Weibull fit better predicts an observed human shift when moving from uniform to enriched or long tails during training. In Experiment 2, more complex 2D rendered face sequences drawn from morph spaces are used as stimuli. Again, the Weibull fit better predicts an observed human shift when training data are sampled differently. An extrema-based model lends new insight into how discriminative information is encoded in the brain with implications for decision making in machine learning.