Extracting Slow Subspaces from Natural Videos Leads to Complex Cells

By Christoph Kayser, Wolfgang Einhäuser, Olaf Dümmer, Peter König, Konrad Paul Kording. 2001

77 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Molecular Biology, Signal Processing

How researchers see this paper

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

In Cognitive Neuroscience

In Molecular Biology

In Signal Processing

Citations in the corpus

Slowness and Sparseness Lead to Place, Head-Direction, and Spatial-View Cells (2007, background): “However, more plausible implementations exist in the form of gradient-descent learning rules [22,38] and as a spike-timing–dependent plasticity rule [23].”
Learning visual groups from co-occurrences in space and time (2015, methodology): “To model w ( A, B ) we use a Convolutional Neural Net (CNN) with a Siamese-style architecture (Figure 2, Chopra et al. (2005)), which we implement in Caffe (Jia et al. (2014)).”
Revisiting Feature Prediction for Learning Visual Representations from Video (2024, methodology): “Early works targeting predictive features encouraged representations of individual video frames to be locally temporally invariant, while preventing representation collapse by using spectral methods, as in SFA (Wiskott and Se-jnowski, 2002), SSA (Kayser et al., 2001), and Simulated Fixations (Zou et”
Learning Invariance from Natural Images Inspired by Observations in the Primary Visual Cortex (2012, methodology): “…Rolls, 1997; Stringer & Rolls, 2000), more recent work is based on natural images and video sequences (Kohonen, 1996; Hyv¨arinen and Hoyer, 2000, 2001; Kayser et al., 2001; Einh¨auser et al., 2002; Hashimoto, 2003; K¨ording et al., 2004; Berkes & Wiskott, 2005; Osindero et al., 2006; Karklin &…”
Learning viewpoint invariant object representations using a temporal coherence principle (2005, methodology): “A number of recent studies exploited this possibility by using different implementations of the temporal coherence principle, such as 'stability' (Kayser et al. 2001, 2003b; Körding et al. 2004), 'slow feature analysis' (Berkes and Wiskott 2003) and a physiologically inspired learning rule…”
Bubbles: a unifying framework for low-level statistical properties of natural image sequences. (2003, unknown): “b~t! 5 f~t! * @s~t!# 2 5 ( t f~t!@s~t 2 t!# 2 . (17) Here f is the low-pass filter in Eq. ( 13 ).”
Invariant Object Recognition with Slow Feature Analysis (2008, methodology): “The slowness principle has been applied in many models of the visual system in the past [11, 12, 13, 5, 6, 2].”
Slowness and Sparseness Have Diverging Effects on Complex Cell Learning (2014, methodology): “Since previous studies have inspected only low spatial frequency filters the different effect of sparseness and slowness has gone unnoticed or at least not been sufficiently appreciated [6,9,29].”
Slow feature analysis yields a rich repertoire of complex cell properties. (2005, background): “We would like to point out that the definitions of slowness in the models described in (Kayser et al., 2001; Einhäuser et al., 2002; Hurri and Hyvärinnen, 2003) and in the present work are to some extent incompatible with each other.”