Independent component filters of natural images compared with simple cells in primary visual cortex

By J. V. van Hateren, A. van der Schaaf. 1998

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Learning Invariant Representations with Local Transformations (2012, methodology): “We visualize the learned TIRBM ﬁlters in Figure 4, where we used the 14 × 14 natural image patches taken from the van Hateren dataset (van Hateren & van der Schaaf, 1998).”
Fast and robust fixed-point algorithms for independent component analysis (1999, methodology): “These applications include artifact ca cellation in EEG and MEG [36], [37], decomposition of evoked fields in MEG [38], and feature extraction of image data [25], [35].”
A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images. (2001, methodology): “…set, since qualitatively similar results have been obtained with different data sets collected by rather different means (Olshausen and Field, 1996; van Hateren and van der Schaaf, 1998; van Hateren and Ruderman, 1998; Hoyer and Hyvärinen, 2000), and one may assume that this robustness should…”
A Structured Model of Video Reproduces Primary Visual Cortical Organisation (2009, background): “The distribution of frequencies is quite broad compared to that found in models based on sparse coding or independent component analysis (ICA) [16,54], where RF frequencies tend to cluster around the highest representable value, and compares well with the width of the distribution in simple cells…”
Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces (2000, methodology): “…scenes, the obtained ﬁlters w i . x ; y / have the three principal properties of simple cells in V1: they are localized, oriented, and bandpass. van Hateren and van der Schaaf (1998) compared quantitatively the obtained ﬁlters w i . x ; y / with those measured by single-cell recordings of the…”
Sparse Filtering (2011, methodology): “In particular, our proposed formulation can be viewed as a re-scaling of the square-root of this measure.”
Toward a unified theory of efficient, predictive, and sparse coding (2017, background): “For natural movies, this leads to neurons selective for a particular motion direction, again similar to observations in area V1 (27).”
Independent Component Analysis (2005, unknown): “Before embarking on an account of the mathematical details of ICA, a simple, intuitive example of how ICA could separate two speech signals is given.”