Reorganizing Neural Network System for Two Spirals and Linear Low-Density Polyethylene Copolymer Problems

Table 2

The produced weight and bias values of the best trained network.

Pressure drop					Shear sftress
Weights			Biases		Weights			Biases
IW{1,1}		LW{2,1}^T	b {1}	b{2}	IW{1,1}		LW{2,1}^T	b{1}	b {2}
–0.0092357	–0.074211	–0.91753	16.5516	1.0932	0.42093	0.11045	–0.29861	–14.8788	0.49395
–0.064121	–0.075615	–1.238	–14.7538		0.14907	–0.028838	0.14388	–12.3761
0.0086149	–0.025249	–2.0174	–2.5568		0.00031069	0.026445	–0.52767	–11.8835
–0.0017662	0.036417	1.4997	–2.6596		–0.0013544	0.0019265	–0.71031	–1.7975
0.023687	–0.0099672	0.58772	–3.0918		–2.385	–2.4141	0.38584	–7.6139
–0.017128	0.0023562	–0.97796	7.6266		0.01941	0.0086871	0.089209	–11.4316
–0.063098	–0.083557	–1.6479	–8.8354		0.0035304	–0.075417	–0.67559	–1.0939
0.20564	0.021342	0.91681	–6.5694		–0.0076158	–0.028539	–0.19949	1.5115
–0.003303	0.022274	1.7385	0.081723		0.044023	0.038829	0.017871	–10.0832
–0.041185	0.079807	1.8449	–11.2574		0.005363	–0.024715	–0.49156	6.6207
0.024424	–0.075788	–1.1288	–2.3592		–0.0013665	0.032209	0.18869	7.0804
0.17343	0.14075	1.9772	1.7446		–0.00048342	–0.00098168	–2.8782	0.41403
–0.011373	–0.02235	–2.4026	9.3959		0.00076532	–0.040128	–0.65477	–1.5022
0.0038815	0.082769	0.97819	8.3238		–0.0081859	0.27396	0.15231	–4.8667
0.0045642	0.081391	0.95285	7.9681		–0.012168	–0.012549	–0.14515	6.2695
–0.0023447	–0.011416	–3.3245	6.9351		0.0038695	0.010562	–0.29916	–3.3411
–0.17721	–0.15542	–1.3838	1.5062		–0.054214	–0.0096744	–0.19168	4.0609
0.013042	0.020739	0.42706	–13.5254		–0.014118	0.015177	0.30145	–5.2238
0.094386	0.060478	1.6078	11.2445		–0.0014922	0.024903	0.32635	–1.9256
0.10412	0.10144	0.4335	5.2448		0.0046948	–0.030181	–0.32884	–0.096699

LW{2,1}^T represents the transpose of LW{2,1}. All names in the above table were described in architecture of the proposed network; see Figure 4.