Adaptive Learning and Pruning Using Periodic Packet for Fast Invariance Extraction and Recognition
CHANG Sheng-Jiang, ZHANG Bian-Li, LIN Lie, XIONG Tao, SHEN Jin-Yuan
Institute of Modern Optics, Nankai University, Tianjin 300071
Key Laboratory of Opto-electronics Information Technical Science (Ministry of Education), Nankai University,
Tianjin 300071
Adaptive Learning and Pruning Using Periodic Packet for Fast Invariance Extraction and Recognition
Institute of Modern Optics, Nankai University, Tianjin 300071
Key Laboratory of Opto-electronics Information Technical Science (Ministry of Education), Nankai University,
Tianjin 300071
Abstract: A new learning scheme using a periodic packet as the neuronal activation function is proposed for invariance extraction and recognition of handwritten digits. Simulation results show that the proposed network can extract the invariant feature effectively and improve both the convergence and the recognition rate.
CHANG Sheng-Jiang;ZHANG Bian-Li;LIN Lie;XIONG Tao;SHEN Jin-Yuan. Adaptive Learning and Pruning Using Periodic Packet for Fast Invariance Extraction and Recognition[J]. 中国物理快报, 2005, 22(2): 295-297.
CHANG Sheng-Jiang, ZHANG Bian-Li, LIN Lie, XIONG Tao, SHEN Jin-Yuan. Adaptive Learning and Pruning Using Periodic Packet for Fast Invariance Extraction and Recognition. Chin. Phys. Lett., 2005, 22(2): 295-297.