Differences

This shows you the differences between two versions of the page.

research:visualstatistician [2010/11/05 12:11]
rosenholtz
research:visualstatistician [2011/10/11 10:19] (current)
rosenholtz
Line 15: Line 15:
There are various benefits to this approach to studying vision.  First and foremost, the resulting models often work quite well.  They often have fewer parameters than neurally inspired models (which often, when analyzed, turn out to be implicitly performing similar calculations).  Statistical models are often surprisingly easy to implement in biologically inspired hardware, and similarly easy to implement in computer vision algorithms which can then make predictions for arbitrarily complex natural images. There are various benefits to this approach to studying vision.  First and foremost, the resulting models often work quite well.  They often have fewer parameters than neurally inspired models (which often, when analyzed, turn out to be implicitly performing similar calculations).  Statistical models are often surprisingly easy to implement in biologically inspired hardware, and similarly easy to implement in computer vision algorithms which can then make predictions for arbitrarily complex natural images.
 +
 +**See the new FAQ [[http://persci.mit.edu/mongrels/about.html|here]].**====
===== Bibliography ===== ===== Bibliography =====
 
research/visualstatistician.1288973510.txt.gz · Last modified: 2010/11/05 12:11 by rosenholtz