A Two-Layer Model of Natural Stimuli Estimated with Score Matching

13 years 2 months ago

Download www.cs.helsinki.fi

We consider a hierarchical two-layer model of natural signals in which both layers are learned from the data. Estimation is accomplished by Score Matching, a recently proposed estimation principle for energy-based models. If the ﬁrst layer outputs are squared and the second layer weights are constrained to be non-negative, the model learns responses similar to complex cells in primary visual cortex from natural images. The second layer pools a small number of features with similar orientation and frequency, but differing in spatial phase. For speech data, we obtain analogous results. The model uniﬁes previous extensions to ICA such as subspace and topographic models and provides new evidence that localized, oriented, phase invariant features reﬂect the statistical properties of natural image patches.

Urs Köster, Aapo Hyvärinen

Real-time Traffic