Chapter 6 Contents
Section 6.1: Learning Rate
Section 6.1.1: An Example
Section 6.1.2: Training Time versus Learning Rate
Section 6.1.3: Interaction of Learning Rate and Momentum
Section 6.1.4: Typical E(t) Curves
Section 6.1.5: Learning Rate Selection
Section 6.1.6: Selection from Trace(H)
Section 6.1.7: Selection by On-Line Eigenvalue Estimation
Section 6.1.8: Delta Attenuation in Layered Networks
Section 6.1.9: Learning Rate Fan-In Scaling
Section 6.2: Momentum
Section 6.3: Remarks