Differences

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

Link to this comparison view

Both sides previous revision Previous revision
feature_binding [2010/05/01 00:03]
sarahsolomon
feature_binding [2010/05/20 09:38] (current)
sarahsolomon
Line 21: Line 21:
 ===Neural Networks: The Competitive Layer Model (CLM)=== ===Neural Networks: The Competitive Layer Model (CLM)===
  
-A different class of feature binding theories are those involving [[Terms and Definitions|neural networks]]. One such network is referred to as the Competitive Layer Model (CLM), and is modeled to reflect the neural correlates of feature binding, thus remaining biologically relevant (Heiko et al, 2001). As the model is too complicated to discuss in detail here, a basic description will be offered. ​+A different class of feature binding theories are those involving [[Terms and Definitions|neural networks]]. One such network is referred to as the Competitive Layer Model (CLM), and is modeled to reflect the neural correlates of feature binding, thus remaining biologically relevant (Wersing ​et al, 2001). As the model is too complicated to discuss in detail here, a basic description will be offered. ​
  
 {{  :​clm_architecture.jpg?​300}} {{  :​clm_architecture.jpg?​300}}
  
-The model implements the principle of topological segregation,​ in which competing groups of [[Terms and Definitions|nodes]] represent different features. These features are selected by columnar circuits spanning the neural layers ,which are referred to as winner-take-all (WTA) circuits. There are lateral interactions within each layer which are involved in encoding the contextual information of the stimulus, and create groupings based on the extent to which the features are similar, or compatible, with one another. When different nodes in a single layer are activated at the same time, those features are bound together. The principle of topological segregation is one that can be implemented in other models besides the CLM, and can be used to augment the stability of other feature binding models (Heiko et al, 2001).+The model implements the principle of topological segregation,​ in which competing groups of [[Terms and Definitions|nodes]] represent different features. These features are selected by columnar circuits spanning the neural layers ,which are referred to as winner-take-all (WTA) circuits. There are lateral interactions within each layer which are involved in encoding the contextual information of the stimulus, and create groupings based on the extent to which the features are similar, or compatible, with one another. When different nodes in a single layer are activated at the same time, those features are bound together. The principle of topological segregation is one that can be implemented in other models besides the CLM, and can be used to augment the stability of other feature binding models (Wersing ​et al, 2001).
  
-The CLM includes self-inhibitory mechanisms as well as Gestalt-based [[Terms and Definitions|figure-ground]] analysis, which enables the model to pick out the most salient features of a stimulus without requiring a biologically unsound number of layers (Heiko et al, 2001). ​+The CLM includes self-inhibitory mechanisms as well as Gestalt-based [[Terms and Definitions|figure-ground]] analysis, which enables the model to pick out the most salient features of a stimulus without requiring a biologically unsound number of layers (Wersing ​et al, 2001). ​