LEARNING IN RECURRENT FINITE DIFFERENCE NETWORKS
1995 ◽
Vol 06
(03)
◽
pp. 249-256
◽
Keyword(s):
A recurrent learning algorithm based on a finite difference discretization of continuous equations for neural networks is derived. This algorithm has the simplicity of discrete algorithms while retaining some essential characteristics of the continuous equations. In discrete networks learning smooth oscillations is difficult if the period of oscillation is too large. The network either grossly distorts the waveforms or is unable to learn at all. We show how the finite difference formulation can explain and overcome this problem. Formulas for learning time constants and time delays in this framework are also presented.
1996 ◽
Vol 127
(1)
◽
pp. 208-217
◽
2020 ◽
Vol 59
(4)
◽
pp. 2409-2417
◽
2020 ◽
Vol 400
◽
pp. 108890
◽
Finite difference discretization of semiconductor drift-diffusion equations for nanowire solar cells
2012 ◽
Vol 183
(10)
◽
pp. 2128-2135
◽
2004 ◽
Vol 25
(12)
◽
pp. 1515-1521
◽
2007 ◽
Vol 24
(1)
◽
pp. 239-248
◽
2004 ◽
Vol 10
(4)
◽
pp. 369-378
◽