Approximation Analysis for a New Kind of Neural Network Using Rational Spline Weight Functions
2014 ◽
Vol 644-650
◽
pp. 1654-1657
Keyword(s):
To describe the performance for a new kind of neural network, This paper discusses the approximation of the neural network using a kind of rational spline weight function. The rational spline consists of piecewise rational functions with cubic numerators and linear denominators. The theoretic formula of approximation is proposed and an example is also given. It can be concluded that this new neural network can get very high training accuracy.
2015 ◽
Vol 713-715
◽
pp. 1708-1711
2014 ◽
Vol 644-650
◽
pp. 1658-1661
2015 ◽
Vol 713-715
◽
pp. 2284-2287
◽
2015 ◽
Vol 713-715
◽
pp. 1813-1816
Keyword(s):
2014 ◽
Vol 989-994
◽
pp. 2659-2662
2014 ◽
Vol 644-650
◽
pp. 2407-2410
Keyword(s):
2015 ◽
Vol 713-715
◽
pp. 1716-1720
Keyword(s):
2014 ◽
Vol 989-994
◽
pp. 2667-2670
2010 ◽
Vol 143-144
◽
pp. 28-31
◽
Keyword(s):
2009 ◽
Vol 12
(3)
◽
pp. 351-364
◽
Keyword(s):