Combining DEKF algorithm and trace rule for fast on-line invariance extraction and recognition

التفاصيل البيبلوغرافية
العنوان: Combining DEKF algorithm and trace rule for fast on-line invariance extraction and recognition
المؤلفون: Kwok-Wo Wong, Chi-Sing Leung, Sheng-Jiang Chang
المصدر: Pattern Recognition Letters. 21:493-501
بيانات النشر: Elsevier BV, 2000.
سنة النشر: 2000
مصطلحات موضوعية: Artificial neural network, Computer science, business.industry, Activation function, Pattern recognition, Invariant (physics), Extended Kalman filter, Artificial Intelligence, Signal Processing, Pattern recognition (psychology), Learning rule, Computer Vision and Pattern Recognition, Artificial intelligence, Sensitivity (control systems), business, Algorithm, Software, Pruning (morphology), TRACE (psycholinguistics)
الوصف: A self-organizing network is used to perform invariance extraction and recognition of handwritten digits. To extract the invariance effectively, we propose to combine the trace learning rule and the on-line dual extended Kalman filter (DEKF) algorithm. Furthermore, a new activation function is suggested to replace the traditional sigmoid activation function so as to reduce the sensitivity of the extracted features to samples with large variance. Computer simulations show that both the learning speed and the recognition rate are improved using a compact network.
تدمد: 0167-8655
DOI: 10.1016/s0167-8655(00)00013-1
URL الوصول: https://explore.openaire.eu/search/publication?articleId=doi_________::0d592f65f06e038f4144cff6ceb826a7
https://doi.org/10.1016/s0167-8655(00)00013-1
Rights: CLOSED
رقم الانضمام: edsair.doi...........0d592f65f06e038f4144cff6ceb826a7
قاعدة البيانات: OpenAIRE
الوصف
تدمد:01678655
DOI:10.1016/s0167-8655(00)00013-1