Earticle

초록

영어

The standard back propagation algorithm for training artificial neural networks utilizes two terms, a learning rate and a momentum factor. The major limitations of this standard algorithm are the existence of temporary, local minima resulting from the saturation behaviour of the activation function, and the slow rates of convergence. Previous research demonstrated that in ‘feed forward’ algorithm, the slope of the activation function is directly influenced by a parameter referred to as ‘gain’. This research proposed an algorithm for improving the performance of the back propagation algorithm by introducing the adaptive gain of the activation function. The efficiency of the proposed algorithm is compared with conventional Gradient Descent Method and verified by means of simulation on four classification problems. In learning the patterns, the simulations result demonstrate that the proposed method converged faster on Wisconsin breast cancer and diabetes classification problem with an improvement ratio of nearly 2.8 and 1.2, 65% better on thyroid data sets and 97% success on IRIS classification problem. The results clearly show that the proposed algorithm significantly improves the learning speed of the conventional back-propagation algorithm.

목차

Abstract
 1. Introduction
 2. Activation Function with Adaptive Gain
 3. Improving Back-propagation Algorithm
  3.1. The Proposed Algorithm
 4. Results and Discussions
  4.1. Breast Cancer Classification Problem
  4.2 IRIS Classification Problem
  4.3 Thyroid Classification Problem
  4.4 Diabetes Classification Problem
 5. Conclusion
 References

키워드

저자

• Nazri Mohd Nawi [ Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia ]
• Norhamreeza Abdul Hamid [ Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia ]
• R.S. Ransing [ Civil and Computational Engineering Centre, School of Engineering Swansea University ]
• Rozaida Ghazali [ Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia ]
• Mohd Najib Mohd Salleh [ Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Database Theory and Application

• 간기

  격월간

• pISSN

  2005-4270

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605