摘要
本文提出了用于无约束手写体数字特征提取和识别的视觉与神经网络混合算法。为了提高不变性特征的稳定性及网络收敛速度 ,我们引入周期包函数来取代传统的 sigmoid激活函数 ,计算机模拟结果显示该算法及激活函数能有效地提取手写体不变性特征 。
A learning algortithm for invariance extraction and recognition of unconstrained handwritten digits is proposed in the article.Furthermore,a novel periodic packet activation funnction is suggested to replace the traditional sigmoid activation function to reduce the sensitivity of the extracted features to samples with large variance and to improve the learning speed.Computer simulations show that the proposed algorithm and activation function are effective on extracting features and improving the learning speed and recognition rate.
出处
《光电子．激光》
EI
CAS
CSCD
北大核心
2001年第12期1280-1283,共4页
Journal of Optoelectronics·Laser
基金
国家自然科学基金资助项目 (698770 0 5 )
