plotep

(To be removed) Plot weight-bias position on error surface

plotep will be removed in a future release. For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.

For advice on updating your code, see Version History.

Syntax

H = plotep(W,B,E)
H = plotep(W,B,E,H)


Description

plotep is used to show network learning on a plot created by plotes.

H = plotep(W,B,E) takes these arguments,

W	Current weight value
B	Current bias value
E	Current error

and returns a cell array H, containing information for continuing the plot.

H = plotep(W,B,E,H) continues plotting using the cell array H returned by the last call to plotep.

H contains handles to dots plotted on the error surface, so they can be deleted next time; as well as points on the error contour, so they can be connected.

Version History

Introduced before R2006a

R2026a: plotep will be removed

plotep will be removed in a future release.

To learn more about visualization workflows, see these examples and topics:

• Deep Learning Visualization Methods

• Explore Network Predictions Using Deep Learning Visualization Techniques

• Deep Learning Metrics

• Monitor Deep Learning Training Progress

• ROC Curve and Performance Metrics

For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.