Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Hopfield networks

Hopfield networks

One of the earliest recurrent neural networks reported in literature was the auto-associator independently described by Anderson and Kohonen. The auto-associator network. All neurons are both input and output neurons, i.e., a pattern is clamped, the network iterates to a stable state, and the output of the network consists of the new activation values of the neurons. The Hopfield network is created by supplying input data vectors, or pattern vectors, corresponding to the different classes. These patterns are called class patterns. In an n-dimensional data space the class patterns should have n binary components {1,-1}; that is, each class pattern corresponds to a corner of a cube in an n-dimensional space. The network is then used to classify distorted patterns into these classes. When a distorted pattern is presented to the network, then it is associated with another pattern. If the network works properly, this associated pattern is one of the class patterns. In some cases (when the different class patterns are correlated), spurious minima can also appear. This means that some patterns are associated with patterns that are not among the pattern vectors. Hopfield networks are sometimes called associative networks since they associate a class pattern to each input pattern.
Use of the Hopfield network
The way in which the Hopfield network is used is as follows. A pattern is entered in the network by setting all nodes to a specific value, or by setting only part of the nodes. The network is then subject to a number of iterations using asynchronous or synchronous updating. This is stopped after a while. The network neurons are then read out to see which pattern is in the network. The idea behind the Hopfield network is that patterns are stored in the weight matrix. The input must contain part of these patterns. The dynamics of the network then retrieve the patterns stored in the weight matrix. This is called Content Addressable Memory (CAM). The network can also be used for auto-association. The patterns that are stored in the network are divided in two parts: cue and association. By entering the cue into the network, the entire pattern, which is stored in the weight matrix, is retrieved. In this way the network restores the association that belongs to a given cue.

Important Note..!

If you are not satisfied with above reply ,..Please


So that we will collect data for you and will made reply to the request....OR try below "QUICK REPLY" box to add a reply to this page
Popular Searches: advantages of hopfield networks, hopfield matlab pattern recognition, advantages and disadvantages of hopfield network, number recognition hopfield matlab, list of seminar paper on nueral network using hopfield network, hopfield seminar, hopfield network tutorial ppt,

Quick Reply
Type your reply to this message here.

Image Verification
Please enter the text contained within the image into the text box below it. This process is used to prevent automated spam bots.
Image Verification
(case insensitive)

Possibly Related Threads...
Thread Author Replies Views Last Post
  Vertical Handoff Decision Algorithm Providing Optimized Performance in Heterogeneous Wireless Networks computer science topics 2 1,356 07-10-2016, 09:02 AM
Last Post: ijasti
  computer networks full report seminar topics 7 5,038 25-05-2016, 02:07 PM
Last Post: dhanyavp
  Dynamic Search Algorithm in Unstructured Peer-to-Peer Networks seminar surveyer 3 1,926 14-07-2015, 02:24 PM
Last Post: seminar report asees
  Heterogeneous Wireless Sensor Networks in a Tele-monitoring System for Homecare electronics seminars 2 1,617 26-02-2015, 08:03 PM
Last Post: Guest
  Shallow Water Acoustic Networks (SWANs project report helper 2 1,121 24-03-2014, 10:10 PM
Last Post: seminar report asees
  Bluetooth Based Smart Sensor Networks (Download Full Seminar Report) Computer Science Clay 75 49,409 16-02-2013, 10:16 AM
Last Post: seminar details
  FACE RECOGNITION USING NEURAL NETWORKS (Download Seminar Report) Computer Science Clay 70 28,116 01-02-2013, 09:28 PM
Last Post: Guest
  Ethernet Passive Optical Networks computer science crazy 1 1,924 12-01-2013, 12:00 PM
Last Post: seminar details
  SEMINAR REPORT on Adaptive Routing in Adhoc Networks Computer Science Clay 2 3,889 02-01-2013, 10:25 AM
Last Post: seminar details
Last Post: seminar details