Beyond weights adaptation: A new neuron model with trainable activation function and its supervised learning

IEEE International Conference on Neural Networks - Conference Proceedings

Volumn 2, Issue , 1997, Pages 1152-1157

  Wu, Youshou ^a   Zhao, Mingsheng ^a   Ding, Xiaoqing ^a  

^a TSINGHUA UNIVERSITY   (China)

Author keywords

[No Author keywords available]

Indexed keywords

ACTIVATION FUNCTIONS; NETWORK CAPACITY; NEURON ACTIVATION FUNCTION; NEURON MODEL; SIMULATION EXAMPLE;

COMPUTER SIMULATION; NEURAL NETWORKS; BACKPROPAGATION; FUNCTIONS; LEARNING ALGORITHMS; MATHEMATICAL MODELS;

NEURONS; NEURAL NETWORKS;

TRAINABLE ACTIVATION FUNCTIONS (TAF);

EID: 0030651089     PISSN: 10987576     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICNN.1997.616194     Document Type: Conference Paper

References (8)

1. Hornik, K., (1991). Approximation capabilities of multilayer feedforward networks, NN, 4, 251-257.
2. Lee, S., & Kil, R. M., (1991). A Gaussian potential function network with hierarchically self-organizing learning. Neural Networks. 4, 207-224.
3. Segee, B.E.(1993), Using spectral techniques for improved performance in ANN. Proc. IEEE 500-505.
4. Stork, D.G., et. al, (1992). How to solve the N-bit parity problem with two hidden units. NN. 5, 923-926.
5. Stork, D.G., (1993). N-bit parity problems: A reply to Brown and Korn, Neural Networks. 6,607-609.
6. Wu, Y.S., (1995). A new approach to design a simplest ANN for performing certain specific problems. Proc. ICONIP'95 Beijing. 1,477-480.
7. Wu, Y.S., (1996). How to choose appropriate transfer function in designing a simplest ANN for solving specific problems. Science in China. Series E., 39(4), 369-372.
8. Wu, Y.S., Zhao, M.S. and Ding, X.Q., (1996). A new kind of multilayer perceptron with tunable activation function and its application. To be appeared in " Science in China", Series E., 40(3), 1997.