netsum

(To be removed) Sum net input function

netsum 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

N = netsum({Z1,Z2,...,Zn},FP) info = netsum('code')

netsum is a net input function. Net input functions calculate a layer’s net input by combining its weighted inputs and biases.

N = netsum({Z1,Z2,...,Zn},FP) takes Z1 to Zn and optional function parameters,

`Zi`	`S`-by-`Q` matrices in a row cell array
`FP`	Row cell array of function parameters (ignored)

and returns the elementwise sum of Z1 to Zn.

info = netsum('code') returns information about this function. The following codes are supported:

netsum('name') returns the name of this function.

netsum('type') returns the type of this function.

netsum('fpnames') returns the names of the function parameters.

netsum('fpdefaults') returns default function parameter values.

netsum('fpcheck', FP) throws an error for illegal function parameters.

netsum('fullderiv') returns 0 or 1, depending on whether the derivative is S-by-Q or N-by-S-by-Q.

Here netsum combines two sets of weighted input vectors and a bias. You must use concur to make b the same dimensions as z1 and z2.

z1 = [1, 2, 4; 3, 4, 1]
z2 = [-1, 2, 2; -5, -6, 1]
b = [0; -1]
n = netsum({z1, z2, concur(b, 3)})

Assign this net input function to the first layer of a network.

net = feedforwardnet(); 
net.layers{1}.netInputFcn = 'netsum';

Introduced before R2006a

collapse all

netsum will be removed in a future release.

To learn more about using activation and transfer functions in neural networks, see these examples and topics: