This article shows analytically that single-cell learning rules that give rise to oriented and localized receptive fields, when their synaptic weights are randomly and independently initialized according to a plausible assumption of zero prior information, will generate visual codes that are invariant under two-dimensional translations, rotations, and scale magnifications, provided that the statistics of their training images are sufficiently invariant under these transformations. Such codes span different image locations, orientations, and size scales with equal economy. Thus, single-cell rules could account for the spatial scaling property of the cortical simple-cell code. This prediction is tested computationally by training with natural scenes; it is demonstrated that a single-cell learning rule can give rise to simple-cell receptive fields spanning the full range of orientations, image locations, and spatial frequencies (except at the extreme high and low frequencies at which the scale invariance of the statistics of digitally sampled images must ultimately break down, because of the image boundary and the finite pixel resolution). Thus, no constraint on completeness, or any other coupling between cells, is necessary to induce the visual code to span wide ranges of locations, orientations, and size scales. This prediction is made using the theory of spontaneous symmetry breaking, which we have previously shown can also explain the data-driven self-organization of a wide variety of transformation invariances in neurons' responses, such as the translation invariance of complex cell response.

Symmetry networks use permutation symmetries among synaptic weights to achieve transformation-invariant response. This article proposes a generic mechanism by which such symmetries can develop during unsupervised adaptation: it is shown analytically that spontaneous symmetry breaking can result in the discovery of unknown invariances of the data's probability distribution. It is proposed that a role of sparse coding is to facilitate the discovery of statistical invariances by this mechanism. It is demonstrated that the statistical dependences that exist between simple-cell-like threshold feature detectors, when exposed to temporally uncorrelated natural image data, can drive the development of complex-cell-like invariances, via single-cell Hebbian adaptation. A single learning rule can generate both simple-cell-like and complex-cell-like receptive fields.