Document Type

Working Paper

Publication Date



Computer vision, Neural networks (Computer science), Mathematical optimization


We investigate the role of learned shape-prototypes in an influential family of hierarchical neural-network models of vision. Central to these networks’ design is a dictionary of learned shapes, which are meant to respond to discriminative visual patterns in the input. While higher-level features based on such learned prototypes have been cited as key for viewpointinvariant object-recognition in these models [1], [2], we show that high performance on invariant object-recognition tasks can be obtained by using a simple set of unlearned, “shape-free” features. This behavior is robust to the size of the network. These results call into question the roles of learning and shapespecificity in the success of such models on difficult vision tasks, and suggest that randomly constructed prototypes may provide a useful “universal” dictionary.


Santa Fe Institute Working Paper 2013-04-013. Subsequently published in Proceedings of the International Joint Conference on Neural Networks (IJCNN), 2013.

Persistent Identifier