Deep Networks as Models of Human and Animal Categorization

Abstract

Convolutional neural networks (CNNs) trained as classifiers learn by associating visual inputs (e.g., photographs of ob- jects) with appropriate output labels (e.g., “crow”, “dog”, “car”). These complex models, which contain millions of weights, are the state-of-the art in machine vision, rivaling humans in object recognition tasks (LeCun, Bengio, & Hinton, 2015; Krizhevsky, Sutskever, & Hinton, 2012). What these networks learn displays some commonalities with hu- man learning (Kubilius, Bracci, & de Beeck, 2016; Lake, Zaremba, Fergus, & Gureckis, 2015). Furthermore, the layers in these networks have been related to neural activity along the ventral stream (Khaligh-Razavi & Kriegeskorte, 2014; Yamins & DiCarlo, 2016)


Back to Table of Contents