TANG Ying, SUN Rongping, and CHEN Kexing, Study on Speeding up the Back-Propagation Algorithm, J. Univ. Sci. Technol. Beijing, 4(1997), No. 4, pp. 52-54.
Cite this article as:
TANG Ying, SUN Rongping, and CHEN Kexing, Study on Speeding up the Back-Propagation Algorithm, J. Univ. Sci. Technol. Beijing, 4(1997), No. 4, pp. 52-54.
TANG Ying, SUN Rongping, and CHEN Kexing, Study on Speeding up the Back-Propagation Algorithm, J. Univ. Sci. Technol. Beijing, 4(1997), No. 4, pp. 52-54.
Citation:
TANG Ying, SUN Rongping, and CHEN Kexing, Study on Speeding up the Back-Propagation Algorithm, J. Univ. Sci. Technol. Beijing, 4(1997), No. 4, pp. 52-54.
Mechanical Engineering School, USTB, Beijing 100083, China
中文摘要
Slow convergence of back-propagation (BP) algorithm is a limiting factor in its practical applications. A new learning algorithm which can adaptively adjust its learning rate on the basis of gradient information of the error function is put forward. its convergence performance is also tested by the XOR problem compared with the standard BP algorithm.
Slow convergence of back-propagation (BP) algorithm is a limiting factor in its practical applications. A new learning algorithm which can adaptively adjust its learning rate on the basis of gradient information of the error function is put forward. its convergence performance is also tested by the XOR problem compared with the standard BP algorithm.
下载: