D. D. Cavilia, M. Valle, and G. M. Bisio, "Effects of Weight Discretization on the Back Propagation Learning Method: Algorithm Design and Hardware Realization," Proc. of the International Joint Conference on Neural Networks, San Diego, CA, Vol. 2, pp. 631-637, 1990. Home/Search Document Not in Database Summary Related Articles |
This paper is cited in the following contexts:
Incremental Communication for Multilayer Neural Networks.. - Ghorbani, Bhavsar (1995) (1 citation) (Correct)
....the communication complexity of ANNs by limiting the node s input output bandwidth requirements. Note that in the incremental communication method all the operations inside a node may be carried out using either full precision or other limited precision strategies suggested in literature [2] [5], 13] 14] 15] 25] It has been shown through simulation that for some problems even 4 bit precision for incremental values in fixed and or floating point representations is sufficient for the network to converge. With 8 12 bit precisions almost the same results August 15, 1997 3 are ....
D. D. Cavilia, M. Valle, and G. M. Bisio, "Effects of Weight Discretization on the Back Propagation Learning Method: Algorithm Design and Hardware Realization," Proc. of the International Joint Conference on Neural Networks, San Diego, CA, Vol. 2, pp. 631-637, 1990.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC