MIT Libraries homeDSpace@MIT

The standard approach to unconstrained face recognition in natural photographs is via a detection, alignment, recognition pipeline. While that approach has achieved impressive results, there are several reasons to be ...

Deep learning networks with convolution, pooling and subsampling are a special case of hierar- chical architectures, which can be represented by trees (such as binary trees). Hierarchical as well as shallow networks can ...

We describe computational tasks - especially in vision - that correspond to compositional/hierarchical functions. While the universal approximation property holds both for hierarchical and shallow networks, we prove that ...

This paper addresses the problem of semantic part parsing (segmentation) of cars, i.e.assigning every pixel within the car to one of the parts (e.g.body, window, lights, license plates and wheels). We formulate this as a ...

Representations in the auditory cortex might be based on mechanisms similar to the visual ventral stream; modules for building invariance to transformations and multiple layers for compositionality and selectivity. In this ...

This paper performs a complexity analysis of a class of serial and parallel compositional models of multiple objects and shows that they enable efficient representation and rapid inference. Compositional models are generative ...

We extend i-theory to incorporate not only pooling but also rectifying nonlinearities in an extended HW module (eHW) designed for supervised learning. The two operations roughly correspond to invariance and selectivity, ...