Advances in Artificial Neural Systems / 2013 / Article / Tab 4

Research Article

Comparison of Artificial Neural Network Architecture in Solving Ordinary Differential Equations

Table 4

Analytical and neural solutions with arbitrary- and regression-based weights (Example 3).

Input data Analytical Euler Runge-KuttaNeural results
  
(four nodes)
  
(four nodes)
  
(five nodes)
  
(five nodes)
  
(six nodes)
  
(six nodes)

0000000000
0.10.06710.10000.06710.04400.05390.07010.06020.05650.0670
0.20.09050.12410.09040.08670.09380.08770.09270.09210.0907
0.30.09170.11690.09170.08490.09260.08890.09320.09310.0918
0.40.08290.09910.08290.08300.08760.08060.08110.08460.0824
0.50.07050.07970.07050.07600.07480.07280.07140.07170.0706
0.60.05780.06220.05770.04920.05990.05290.05930.05360.0597
0.70.04610.04760.04610.04330.04790.04100.04530.04500.0468
0.80.03620.03600.03620.03370.03190.03720.03700.03430.0355
0.90.02800.02710.02800.03240.03080.03090.02640.02490.0284
1.00.02150.02030.02150.03040.02820.02550.02470.02320.0217

We are committed to sharing findings related to COVID-19 as quickly as possible. We will be providing unlimited waivers of publication charges for accepted research articles as well as case reports and case series related to COVID-19. Review articles are excluded from this waiver policy. Sign up here as a reviewer to help fast-track new submissions.