Training algorithm for perceptron with multi-pulse type activation function
- 5 Downloads
The conventional perceptron with the sign type activation function can be used for performing the linearly separable pattern recognition with its weight vector being found by the conventional perceptron training algorithm. On the other hand, the perceptron with the multi-pulse type activation function can be used for performing the piecewise linearly separable pattern recognition. This paper proposes a training algorithm for finding its weight vector. Moreover, some application examples of this perceptron are given for the demonstration purpose.
KeywordsPiecewise linearly separable pattern recognition Perceptron training algorithm Perceptron with the multi-pulse type activation function
This paper was supported partly by the National Nature Science Foundation of China (Nos. U1701266, 61372173 and 61671163), the Team Project of the Education Ministry of the Guangdong Province (No. 2017KCXTD011), the Guangdong Higher Education Engineering Technology Research Center for Big Data on Manufacturing Knowledge Patent (No. 501130144) and Hong Kong Innovation and Technology Commission, Enterprise Support Scheme (No. S/E/070/17).
- 5.Freund, Y., Schapire. R.E.: Large margin classification using the perceptron algorithm. In: Proceedings of the 11th Annual Conference on Computational Learning Theory. ACM Press (1998)Google Scholar
- 6.Li, Y.Y., Zaragoza, H., Herbrich, R., Shawe-Taylor, J., Kandola, J.: The perceptron algorithm with uneven margins. In: Proceedings of the 19th International Conference on Machine Learning, pp. 379-386 (2002)Google Scholar
- 24.Zhao, Y., Deng, B., Wang, Z.: Analysis and study of perceptron to solve XOR problem. In: The 2nd International Workshop on Autonomous Decentralized System, pp. 168–173 (2002)Google Scholar