Evolutional design and training algorithm for feedforward neural networks

IEICE Transactions on Information and Systems

Volumn E82-D, Issue 10, 1999, Pages 1384-1392

  Takahashi, Hiroki ^a   Nakajima, Masayuki ^a  

^a TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Designing neural networks; Evolutional computation; Feedforward neural network; Handwritten character recognition; Training neural networks

Indexed keywords

EID: 0000566199     PISSN: 09168532     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (16)

1. T. Agui, T. Kakuyama, H. Nagahashi, and T. Nagao, "A study on learning of neural networks using a genetic algorithm," J. IIEEJ, vol.23, no.2, pp.96-101, 1994.
2. T. Agui, H. Takahashi, M. Nakajima, and H. Nagahashi, "Recognition of handwritten KATAKANA in a frame using moment invariants based on neural network," SPIE Visual Communications and Image Processing '91, vol.1606, no.l, pp.188-197, 1991.
3. M. Fukumi and N. Akamatsu, "A genetic algorithm with deterministic mutation based on neural network learning," IEICE Trans., vol.J80-D-II, no.10, pp.2800-2807, Oct. 1997.
4. S.A. Harp, T. Samad, and A. Guha, "Towards the genetic synthesis of neural networks," Proc. of ICGA-89, pp.360369, 1989.
5. H. Kitano, "Designing neural networks using genetic algorithms with graph generation system," Complex Systems, vol.4, pp.461-476, 1990.
6. T. Kurita, "A method to determine the number of hidden units of three layered neural networks by information criteria," IEICE Trans., vol.J73-D-II, no.ll, pp.1872-1878, Nov. 1990.
7. Y. Matsunaga, K. Murase, O. Yamakawa, and M. Tanifuji, "A modified back-propagation algorithm that automatically removes redundant hidden units by competition," IEICE Trans., vol.J79-D-II, no.3, pp.403-412, March 1996.
8. G.F. Miller, P.M. Todd, and S.U. Hegde, "Designing neural networks using genetic algorithms," the 3rd International Conference on Genetic Algorithms, pp.379-384, 1989.
9. D.J. Montana and L.D. Davis, "Training feedforward neural networks using genetic algorithms," Proc. of llth International Conference on Artificial Intelligence, vol.1, pp.762767, 1989.
10. T. Nagao, T. Agui, and H. Nagahashi, "Structural evolution of neural networks by a genetic method," IEICE Trans., V01.J75-D-II, no.9, pp.1634-1637, Sept. 1992.
11. T. Nagao, T. Agui, and H. Nagahashi, "Structural evolution of neural networks having arbitrary connections by a genetic method," IEICE Trans., vol.E76-D, no.6, pp.C89-G97, June 1993.
12. T. Nagao, T. Agui, and H. Nagahashi, "An automatic GA-based construction of neural networks for motion control of virtual life," IEICE Trans., vol.J78-D-II, no.7, pp.1150-1152, July 1995.
13. J. Okamoto, Y. Sugimoto, and S. Hosokawa, "A learning method for a feed forward typo neural network by GA," IEICE Trans., vol.J77-D-II, no.2, pp.461-465, Feb. 1991.
14. D.E. Rtimelhart, G.E. Hinton, and R.J. Williams, Learning internal representations by error propagation, MIT Press, Cambridge, MA, pp.318-362, 1986.
15. H. Takahashi and M. Nakajima, "A study of designing feedforward neural networks using genetic algorithm," IEICE Trans., vol.J79-D-II, no.ll, pp.1920-1928, Nov. 1996.
16. [1C] V. Williams, T. Tokunari, and K. Matsuoka, "Learning of neural nets by genetic algorithm," IEICE Technical Report, NC-91-77, 1991.