| Título: | Knowledge Extraction From Trained Neural Networks |
| Autores: | kumar, koushal; Lovely Professional University |
| Fecha: | 2012-09-14 |
| Publicador: | International journal of information and network security |
| Fuente: |
 |
| Tipo: |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
| Tema: | No aplica |
| Descripción: | Artificial neural networks (ANN) are very efficient in solving various kinds of problems But Lack of explanation capability (Black box nature of Neural Networks) is one of the most important reasons why artificial neural networks do not get necessary interest in some parts of industry. In this work artificial neural networks first trained and then combined with decision trees in order to fetch knowledge learnt in the training process. After successful training, knowledge is extracted from these trained neural networks using decision trees in the forms of IF THEN Rules which we can easily understand as compare to direct neural network outputs. We use decision trees to train on the results set of trained neural network and compare the performance of neural networks and decision trees in knowledge extraction from neural networks. Weka machine learning simulator with version 3.7.5 is used for research purpose. The experimental study is done on bank customers’ data which have 12 attributes and 600 instances. The results study show that although neural networks takes much time in training and testing but are more accurate in classification then decision trees. |
| Idioma: | Inglés |
1 Improved G-3PAKE Protocol with Formal Verification por Sanghi, Manju | 6 Developing a Secure Programming Module to cope with Modern Vulnerabilities por McKelvey, Nigel; Letterkenny Institute of Technology |
2 New GSM, DCS and GSM/DCS Pifa Antennas Designs for Wireless Networks Applications por Mehadji, Abri; Tlemcen university,Belgacem, N; Tlemcen university,Belgacem, W; Tlemcen university | 7 A New Proxy Blind Signature Scheme Based on DLP por VERMA, SWATI; "Pt.Ravishankar Shukla University, Raipur(Chhattisgarh)",Sharma, Birendra Kumar; "Pt.Ravishankar Shukla University, Raipur(Chhattisgarh)" |
3 | 8 A Comprehensive Study of Social Engineering Based Attacks in India to Develop a Conceptual Model por Chitrey, Anubhav; Department of Information Security & Cyber Law
Indian Institute of Information Technology
Allahabad, India,Singh, Dharmendra,Singh, Vrijendra |
4 Synthetic Feature Transformation with RBF neural network to improve the Intrusion Detection System Accuracy and Decrease Computational Costs por Asgari Taghanaki, Saeid; IAU Majlesi,Zamani Dehkordi, Behzad,Hatam, Ahmad,Bahraminejad, Behzad | 9 Fast Mapping Method based on Matrix Approach For Elliptic Curve Cryptography por El Kinani, El Hassan; Groupe algèbre et Applications
Département de Mathématiques
Faculté des Sciences et Techniques
Univesité Moulay Ismaïl
Errachidia. Maroc. |
5 A Password attack on S-3 PAKE Protocol por Tallapally, Shirisha | 10 Effective Performance of Dynamic Source Routing Protocol on Random Waypoint Model (RWM) Using CBR por kumar, jogendra; CSED |