Sparse coding of natural contours
<br>
<br>

                          Patrik Hoyer
<br>
                 Neural Networks Research Centre
<br>
                Helsinki University of Technology
<br>
<br>

                    2:30pm, Thursday, July 11
<br>
                   CNS classroom (Meyer, 815)
<br>
<br>

An important approach in visual neuroscience considers how the
function of the early visual system relates to the statistics of its
natural input. After reviewing previous studies showing how neural
receptive fields in the primary visual cortex can be understood as
efficient coding of natural images, I will consider how similar
principles might be used to predict extrastriate receptive field
properties. As a very first step in that direction, we have applied
sparse coding to the responses of hypothetical complex cells to
natural images. This leads to contour coding and end-stopped receptive
fields.