View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation
This addresses a gap in computational models of primate vision for neuroscientists and AI researchers, though it is incremental as it builds on existing hierarchical architectures.
The study tackled the problem of how neural networks can achieve mirror-symmetric tuning to head orientation in face recognition, unlike current models, and proved that a specific Hebbian learning rule generates this property in intermediate representations.
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. 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. 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. 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.