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

Practical Neural Network Recipies in C++

by Masters
June 2014
Intermediate to advanced
493 pages
20h 30m
English
Morgan Kaufmann
Content preview from Practical Neural Network Recipies in C++
Functional
Link
Networks
229
input. There is no restriction that the same function or set of
functions must be used for each input. Thus, we can have
//(·^o>···
,
x
m-0
=
£o,fv*o)*
'
=
"»···»
k-l
9
\?>-5
fi+k&o* ···»
x
m-i '
=
8i
f
i\
x
\)
*
i
=
">····
'
and so forth for all desired fimctions.
There are two commonly used sets of functions for this model.
One is the polynomial series:
g
M
(x)
=
x
k
+
l
,
j = 0,..., m-1 ; k = 0,... 13-6
A few words about the polynomial series are in order. If
powers higher than three or so are used (not generally recommended),
the system of equations starts to become numerically unstable. Rather
than using individual polynomia ...
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

Data Clustering in C++

Data Clustering in C++

Guojun Gan
Wireless Network Simulation: A Guide using Ad Hoc Networks and the ns-3 Simulator

Wireless Network Simulation: A Guide using Ad Hoc Networks and the ns-3 Simulator

Henry Zárate Ceballos, Jorge Ernesto Parra Amaris, Hernan Jiménez Jiménez, Diego Alexis Romero Rincón, Oscar Agudelo Rojas, Jorge Eduardo Ortiz Triviño

Publisher Resources

ISBN: 9780080514338