Skip to Main Content
Practical Neural Network Recipies in C++
book

Practical Neural Network Recipies in C++

by Masters
June 2014
Intermediate to advanced content levelIntermediate to advanced
493 pages
20h 30m
English
Morgan Kaufmann
Content preview from Practical Neural Network Recipies in C++
94
Chapter 6
a derivative becoming nearly 0, so that weight would become stuck out
in left field. Keeping the function value away from extremes prevents
this occurrence. The exact point at which this limit is imposed is not
critical; the value of 10 shown here should be generally applicable.
In case there is extremely limited memory available, it is not
necessary to precompute f_d, the difference table. This would cut the
memory requirement in
half.
The difference could be computed as
M[i+1] -
f_f[i]
when it is needed in the interpolation. Having it
available in a table slightly speeds execution, but is certainly not
necessary.
One annoyanc ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Neural Networks with Keras Cookbook

Neural Networks with Keras Cookbook

V Kishore Ayyadevara
Scientific Computing with Python 3

Scientific Computing with Python 3

Claus Führer, Claus Fuhrer, Jan Erik Solem, Olivier Verdier
Mastering Java Machine Learning

Mastering Java Machine Learning

Uday Kamath, Krishna Choppella

Publisher Resources

ISBN: 9780080514338