What is meant by Manhattan update rule in neural networks ?

[vetriece86@gmail.com]

Could anyone explain me about

1. What is meant by Manhattan update rule ?

2. How to use Manhattan update rule in delta rule ?

Thank you.

 

[D.A.(Tony)Stewart]

Been there.. But never tried it

**broken link removed**

it seems no delta on estimate just polarity.
To converge the estimate STEP SIZE is incremented each time.

seems like a simple but slow method but resilient

like dynamic RAM Virtual Memory size reserve estimates.... Adapt with margin , grow by increasing larger steps at some rate until converge on desired value

, stable, resilient , wide range

not sure if step size reset to base increment on polarity toggle.. Probably

 

[vetriece86@gmail.com]

Even I too read that Pdf. But I didnt understand. If possible, can you explain me in short about Manhattan update rule.

 

[D.A.(Tony)Stewart]

Ok , we both learned something