View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation

TitleView-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation
Publication TypeCBMM Memos
Year of Publication2016
AuthorsLeibo, JZ, Liao, Q, Freiwald, WA, Anselmi, F, Poggio, T
Date Published06/2016
Abstract

The primate brain contains a hierarchy of visual areas, dubbed the ventral stream, which rapidly computes object representations that are both specific for object identity and relatively robust against identity-preserving transformations like depth-rotations [ 33 , 32 , 23 , 13 ]. Current computational models of object recognition, including recent deep learning networks, generate these properties through a hierarchy of alternating selectivity-increasing filtering and tolerance-increasing pooling operations, similar to simple-complex cells operations [ 46 , 8 , 44 , 29 ]. While simulations of these models recapitulate the ventral stream’s progression from early view-specific to late view-tolerant representations, they fail to generate the most salient property of the intermediate representation for faces found in the brain: mirror-symmetric tuning of the neural population to head orientation [ 16 ]. Here we prove that a class of hierarchical architectures and a broad set of biologically plausible learning rules can provide approximate invariance at the top level of the network. While most of the learning rules do not yield mirror-symmetry in the mid-level representations, we characterize a specific biologically-plausible Hebb-type learning rule that is guaranteed to generate mirror-symmetric tuning to faces tuning at intermediate levels of the architecture.

arXiv

arXiv:1606.01552v1 [cs.NE]

DSpace@MIT

http://hdl.handle.net/1721.1/103394

Download: 

CBMM Memo No: 

049

Research Area: 

CBMM Relationship: 

  • CBMM Funded