Team:USP-UNESP-Brazil/Associative Memory/Background

From 2012.igem.org

(Difference between revisions)
(Hopfield Associative Memory Networks)
(Hopfield Associative Memory Networks)
Line 7: Line 7:
[[File:equation1.jpg|center|300px|caption|]]
[[File:equation1.jpg|center|300px|caption|]]
 +
Equation 1
   
   
Where “w” values are chosen such that the stored settings are the minima of the function “E”. The variable “x” is the state of the neuron “i”.  
Where “w” values are chosen such that the stored settings are the minima of the function “E”. The variable “x” is the state of the neuron “i”.  
Line 13: Line 14:
   
   
[[File:equation2.jpg|center|400px|caption|]]
[[File:equation2.jpg|center|400px|caption|]]
 +
Equation 2
In this equation, “wij” is the wheight
In this equation, “wij” is the wheight
Line 23: Line 25:
[[File:equation3.png|center|400px|caption|]]
[[File:equation3.png|center|400px|caption|]]
 +
Equation 3
-
The figure below shows the selection process of weights of connections between adjacent cells. To add more patterns, we have to sum the network of weights of the new pattern to the old network. (as shown in last picture)
+
The Figure 1w shows the selection process of weights of connections between adjacent cells. To add more patterns, we have to sum the network of weights of the new pattern to the old network. (as shown in the Figure 2)
[[File:009.JPG|center|570px|caption|]]
[[File:009.JPG|center|570px|caption|]]
 +
Figure 1
The Hopfield model for the construction of an associative memory network using bacteria is a good choice because of its simplicity and strength. The same methodology can be used to the construction of networks with other architectures, such as the “perceptrons”. One step forward is the way how to deal with continuous biological variables, because the standard model uses discrete ones.
The Hopfield model for the construction of an associative memory network using bacteria is a good choice because of its simplicity and strength. The same methodology can be used to the construction of networks with other architectures, such as the “perceptrons”. One step forward is the way how to deal with continuous biological variables, because the standard model uses discrete ones.
[[File:0018.JPG|center|620px|caption|]]
[[File:0018.JPG|center|620px|caption|]]
 +
Figure 2

Revision as of 15:54, 22 September 2012