Hopfield Neural Network as Associated Memory with Monte Carlo- (MC-)Adaptation Rule and Genetic Algorithm for pattern storage
Journal Title: International Journal of Research in Computer and Communication Technology - Year 2013, Vol 2, Issue 8
Abstract
This paper describes the performance analysis of Hopfield neural networks by usinggenetic algorithm and Monte Carlo-(MC-) adaptation learning rule.A set of five objects has been considered as the pattern set. In the Hopfield type of neural networks of associative memory, the weighted code of input patterns provides an auto-associative function in the network. The storing of the objects has been performed using Hebbian rule and recalling of these stored patterns on presentation of prototype input patterns has been made using both - conventional hebbian rule and geneticalgorithm.In most cases, the recalling of patterns using genetic algorithm with MC-adaptation rule seems to give better results than the conventional hebbian rule, MC-adaptation rule and simple genetic algorithm recalling techniques.
Authors and Affiliations
Manisha Uprety, Somesh Kumar
Keywords
Related Articles
- EP ID EP27627
- DOI -
- Views 302
- Downloads 4
A Novel Grid Synchronization System under Adverse Grid Conditions
Grid synchronization algorithms are of great importance in the control of grid-connected power converters, as fast and accurate detection of the grid voltage parameters is crucial in order to implement stable control...
New architecture and efficient inter device communication for content transferring in human networks
We present B-SUB, an interest-driven information sharing system for HUNETs, which stands for the bloom-filter-based publish/SUBscribe. B-SUB is calculated for small to medium sized networks selfpossessed of dozens of...
Survey on Suspicious URL Detection Schemes in Twitter Stream
Twitter is a micro-blogging and online social networking service that enables its users to send and read "tweets”. Tweets are text messages limited to 140 characters. Twitter is prone to a lot of malicious tweets whi...
Information Mining Thorugh Big Data
Big Data is another term used to recognize the datasets that because of their extensive size and multifaceted nature. Huge Data are currently quickly extending in all science and building spaces, including physical,...
Web Application: Performance Testing Using Reactive Based Framework
Web application performance testing plays an important role in providing Quality of Service (QoS). Performance testing is very important for satisfying users. This research paper presents performance testing of web a...