CNS Seminar

I-theory starts from the hypothesis that invariant representations of images are the main computational goal of the ventral stream in visual cortex. Invariant representations can be proved to lead to lower sample complexity in image recognition. We propose a biologically plausible simple-complex cells module (HW module) for computing components of an invariant signature. For transformations that have the structure of a locally compact group we prove invariance and selectivity, showing how a hierarchical architecture of HW modules can learn in an unsupervised way to be automatically invariant to transformations of a new object, achieving the goal of recognition with very few labeled examples. I-theory makes specific predictions about the hierarchical architecture of the ventral stream, including the dependence on eccentricity of the magnification factor in various areas, and on the tuning properties of its neurons from early generic, Gabor-like tuning to class-specific tuning in AIT.

This approach is an example of what could be the next phase in the theory of learning: how to learn in an unsupervised way good representations that allow a supervised classifier to learn from very few labeled examples, similar to how children learn.