Subscribe to Vincent Granville's Weekly Digest:

Neural Nets Tips and Tricks: add recall Output neuron

...

As mentioned, in many cases the customization of algorithms is the only way to achieve the target, but sometimes, some tricks can help to improve the learning even without changes of learning strategy!
Consider for example our XOR problem solved through neural networks.
Let's see how we can reduce considerably the epochs required to train the net.

read more here: http://textanddatamining.blogspot.com/

Here some results:

Original configuration (convergence after 600 cycles)

Net with recall neuron: convergence after 150 cycles.

The surface error for the most important synapses: (notice how the error slumps quickly)

Views: 321

Tags: Back, Neural, Propagation, networks

Comment

You need to be a member of AnalyticBridge to add comments!

Join AnalyticBridge

Follow us

© 2013   AnalyticBridge.com is a subsidiary and dedicated channel of Data Science Central LLC

Badges  |  Report an Issue  |  Terms of Service