Comparison of variable learning rate and Levenberg-Marquardt back-propagation training algorithms for detecting attacks in Intrusion Detection Systems
Journal Title: International Journal on Computer Science and Engineering - Year 2011, Vol 3, Issue 11
Abstract
This paper investigates the use of variable learning rate back-propagation algorithm and Levenberg-Marquardt back-propagation algorithm in Intrusion detection system for detecting attacks. In the present study, these 2 neural network (NN) algorithms are compared according to their speed, accuracy and, performance using mean squared error (MSE) (Closer the value of MSE to 0, higher will be the performance). Based on the study and test results, the Levenberg-Marquardt algorithm has been found to be faster and having more accuracy and performance than variable learning rate backpropagation algorithm.
Authors and Affiliations
Tummala Pradeep , P. Srinivasu , P. S. Avadhani , Y. V. S. Murthy
Keywords
Related Articles
- EP ID EP103028
- DOI -
- Views 117
- Downloads 0
DERIVATION OF CUSTOMER INTELLIGENCE FROM CUSTOMER KNOWLEDGE MANAGEMENT
In today’s world, knowledge has turned into a main element of the financial management. In fact, knowledge is the most essential strategic asset and the capacity to pick up and extend it, spread and apply it can remain t...
Sequence Related IT Functions for String Based Update Operations by New Operational Transformation Algorithms for Wide-Area Collaborative Applications
Operational transformation (OT) is an established optimistic consistency control method in collaborative applications. This approach requires correct transformation functions. In general all OT algorithms only consider t...
Frequent Itemset mining over transactional data streams using Item-Order-Tree
The association rule mining is one of the important area for research in data mining. In association rule mining online association rule mining is one of the hottest area due to the reason that the knowledge embedded in...
Zone Routing Protocol Using Anycast Addressing For Ad-Hoc Network
Zone Routing Protocol (ZRP) is a hybrid protocol that combines the advantages of both the proactive and reactive protocols. It is classified as: Intra Zone Routing, which uses hop count of the Nneighbors using proactive...
FEATURE BASED IMAGE OPTIMIZATION TECHIQUE
The motivation behind the production of high resolution images is to increase the quality and the visual presentation of a digital image. The erstwhile analogue images captured by the silver Bromide film was having infin...