GENERALIZATION OF LINEAR REGRESSION PROBLEMS - Neural-based Orthogonal Data Fitting: The EXIN Neural Networks - page 201

0.7

0.6

0.5

0.4

0

0.3

0.5

0.2 1

0.1

0

0 0.2 0.4 0.6 0.8 1 1.2

Figure 5.29 Phase diagram of the weights of DLS scheduling EXIN for the benchmark
problem (hyperbolic scheduling and null initial conditions). The solution locus is indicated
together with the OLS, TLS, and DLS solutions.

OLS : SCG(solid), BFGS(dashed)

0.8

x1 x1

0.7

0.6

0.5

0.4

x2 x2

0.3

0.2

0.1

0

0 1 2 3 4 5

epochs

6 7 8 9

Figure 5.30 Plot of the weights of SCG and BFGS EXIN for the OLS benchmark problem.
( See insert for color representation of the figure .)