assosiative memory network - Associative Memory Networks Dr K Ganesan Director TIFAC-CORE in Automotive Infotronics VIT University Vellore 632 014

assosiative memory network - Associative Memory Networks Dr...

This preview shows page 1 - 7 out of 121 pages.

Associative Memory Networks Dr. K. Ganesan Director – TIFAC-CORE in Automotive Infotronics VIT University, Vellore – 632 014 [email protected]
Image of page 1
Introduction An associative memory network can store a set of patterns as memories. When the associative memory is being presented with a key pattern, it responds by producing one of the stored patterns, which closely resembles or relates to the key pattern. Thus, the recall is through association of the key pattern, with the help of information memorized. These type of memories are also called as content-addressable memories (CAM) in contrast to that of traditional address- addressable memories in digital computers where stored pattern (in bytes) is recalled by its address.
Image of page 2
CAM The CAM can also be viewed as associating data to address, ie, for every data in the memory there is a corresponding unique address. It can be viewed as a data correlator. Here input data is correlated with that of the stored data in the CAM. It should be noted that the stored pattern must be unique, ie different patterns in each location. Associative memory makes a parallel search within a stored data file. The idea is to retrieve any one or all stored items which match the given search argument.
Image of page 3
Types of associative memories There are two types of associative memories. They are autoassociative memory and heteroassociative memory. Both these nets are single-layer nets in which the weights are determined in a manner that the net stores a set of pattern associations. Each of these association is an input-output vector pair, say, s:t. If each of the output vectors is same as the input vectors with which it is associated, then the net is said to be auto associative memory net. If the output vectors are different from the input vectors then the net is said to be heteroassociative memory net.
Image of page 4
Hamming distance If there exist vectors, say, x = (x1, x2, …, xn)T and x’ = (x1’, x2’, …, xn’) T then the Hamming distance (HD) is defined as the number of mismatched components of x and x’ vectors, ie, HD(x, x’) =∑ |xi – xi’| if xi, xi’ ε [0,1] for i varying from 1 to n. = 0.5* ∑ |xi – xi’| if xi, xi’ ε [-1,0] for i varying from 1 to n. The architecture of an associate net may be either feed- forward or iterative (recurrent). In a feed-forward net the information flows from the input units to the output units, but in a recurrent neural net, there are connections among the units to form a closed loop structure.
Image of page 5
Training algorithms for Pattern Association There are 2 algorithms developed for training of pattern association nets. They are : Hebb rule and Outer products rule. Hebb Rule The training algorithm is given below: Step 0: Set all the initial weights to zero, ie, wij = 0 (i =1 to n, j = 1 to M) Step 1: For each training target input output vector pairs s:t, perform Steps 2-4.
Image of page 6
Image of page 7

You've reached the end of your free preview.

Want to read all 121 pages?

  • Winter '16
  • ganeshan
  • Neural Networks, associative memory, Hopfield net

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern

Stuck? We have tutors online 24/7 who can help you get unstuck.
A+ icon
Ask Expert Tutors You can ask You can ask You can ask (will expire )
Answers in as fast as 15 minutes
A+ icon
Ask Expert Tutors