A new backpropagation learning algorithm for layered neural networks with nondifferentiable units

Neural Computation

Volumn 19, Issue 5, 2007, Pages 1422-1435

  Oohori, Takahumi ^a   Naganuma, Hidenori ^a   Watanabe, Kazuhisa ^a  

^a HOKKAIDO INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; BIOLOGICAL MODEL; COMPUTER SIMULATION; HUMAN; INFORMATION PROCESSING; LEARNING; NERVE CELL NETWORK; PHYSIOLOGY;

ALGORITHMS; AUTOMATIC DATA PROCESSING; COMPUTER SIMULATION; HUMANS; LEARNING; MODELS, NEUROLOGICAL; NERVE NET; NEURAL NETWORKS (COMPUTER);

EID: 34247887369     PISSN: 08997667     EISSN: 1530888X     Source Type: Journal    
DOI: 10.1162/neco.2007.19.5.1422     Document Type: Article

References (11)

1. Amari, S. (1978). Mathematical Theory of Nerve Nets. Tokyo: Sangyotosho. (In Japanese.)
2. Jacobs, R. (1988). Increased rates of convergence through learning rate adoption. Neural Networks, 1, 295-307.
3. Minsky, M., & Papert, S.(1969). Perceptions. Cambridge, MA: MIT Press.
4. Oohori, T., Kamada, S., Kobayashi, Y., Konishi, Y, & Watanabe, K. (2000). A new error back propagation learning algorithm for a layered neural network with nondifferentiable units (Tech. rep. NC99-85). Tokyo: Institute of Electronics, Information, and Communications Engineers.
5. Rosenblatt, F. (1961). Principles of neurodynamics. Spartan.
6. Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representation by back-propagation errors. Nature, 323, 533-536.
7. Vogl, T. P., Mangis, J. K., Rigler, A. K., Zink, W. T., & Alkon, D. L. (1988). Accelerating the convergence of the backpropagation method. Biological Cybernetics, 59, 257-263.
8. Watanabe, K., Furukawa, T., Mitani, M., & Oohori, T., (1997). Fluctuation-driven learning for feedforward neural networks. IEICE Trans. on Information and System, J80-D-II, 1249-1256.
9. Widrow, B, Winter, R. G., & Baxter, R. A. (1988). Layered neural nets for pattern recognition. IEEE Trans. Acoustic, Speech and Signal Processing, ASSP-36, 1109-1118.
10. Yamada, K., Kuroyanagi, S., & Iwata, A. (2004). A supervised learning method using duality in the artificial neuron model. IEICE Trans. on Information and System, J87-D-11, 399-406.
11. Zeng, Z., Goodman, R. M., & Smyth, P. (1993). Learning finite state machines with self-clustering networks. Neural Computation, 5, 976-990.