10/29/2018 Create custom neural network - MATLAB network

network
Create custom neural network

Syntax
net = network
net = network(numInputs,numLayers,biasConnect,inputConnect,layerConnect,outputConnect)

To Get Help
Type help network/network.

 Tip
To learn how to create a deep learning network, see Specify Layers of Convolutional Neural Network.

Description
network creates new custom networks. It is used to create networks that are then customized by functions such as
feedforwardnet and narxnet.

net = network without arguments returns a new neural network with no inputs, layers or outputs.

net = network(numInputs,numLayers,biasConnect,inputConnect,layerConnect,outputConnect) takes these

optional arguments (shown with default values):

numInputs Number of inputs, 0

numLayers Number of layers, 0

biasConnect numLayers-by-1 Boolean vector, zeros

inputConnect numLayers-by-numInputs Boolean matrix, zeros

layerConnect numLayers-by-numLayers Boolean matrix, zeros

outputConnect 1-by-numLayers Boolean vector, zeros

and returns

net New network with the given property values

Properties

Architecture Properties
net.numInputs 0 or a positive integer Number of inputs.

net.numLayers 0 or a positive integer Number of layers.

net.biasConnect numLayer-by-1 Boolean If net.biasConnect(i) is 1, then layer i has a bias, and

vector net.biases{i} is a structure describing that bias.

net.inputConnect numLayer-by-numInputs If net.inputConnect(i,j) is 1, then layer i has a weight

Boolean vector coming from input j, and net.inputWeights{i,j} is a
structure describing that weight.

http://www.mathworks.com/help/deeplearning/ref/network.html;jsessionid=0e8ce9952d7915d2fe746ae2fa54 1/4
10/29/2018 Create custom neural network - MATLAB network

net.layerConnect numLayer-by-numLayers If net.layerConnect(i,j) is 1, then layer i has a weight

Boolean vector coming from layer j, and net.layerWeights{i,j} is a
structure describing that weight.

net.numInputs 0 or a positive integer Number of inputs.

net.numLayers 0 or a positive integer Number of layers.

net.biasConnect numLayer-by-1 Boolean If net.biasConnect(i) is 1, then layer i has a bias, and

vector net.biases{i} is a structure describing that bias.

net.inputConnect numLayer-by-numInputs If net.inputConnect(i,j) is 1, then layer i has a weight

Boolean vector coming from input j, and net.inputWeights{i,j} is a
structure describing that weight.

net.layerConnect numLayer-by-numLayers If net.layerConnect(i,j) is 1, then layer i has a weight

Boolean vector coming from layer j, and net.layerWeights{i,j} is a
structure describing that weight.

net.outputConnect 1-by-numLayers Boolean If net.outputConnect(i) is 1, then the network has an

vector output from layer i, and net.outputs{i} is a structure
describing that output.

net.numOutputs 0 or a positive integer (read Number of network outputs according to net.outputConnect.

only)

net.numInputDelays 0 or a positive integer (read Maximum input delay according to all

only) net.inputWeights{i,j}.delays.

net.numLayerDelays 0 or a positive number (read Maximum layer delay according to all

only) net.layerWeights{i,j}.delays.

Subobject Structure Properties

net.inputs numInputs-by-1 cell array net.inputs{i} is a structure defining input i.

net.layers numLayers-by-1 cell array net.layers{i} is a structure defining layer i.

net.biases numLayers-by-1 cell array If net.biasConnect(i) is 1, then net.biases{i} is a

structure defining the bias for layer i.

net.inputWeights numLayers-by-numInputs If net.inputConnect(i,j) is 1, then

cell array net.inputWeights{i,j} is a structure defining the weight to
layer i from input j.

net.layerWeights numLayers-by-numLayers If net.layerConnect(i,j) is 1, then

cell array net.layerWeights{i,j} is a structure defining the weight to
layer i from layer j.

net.outputs 1-by-numLayers cell array If net.outputConnect(i) is 1, then net.outputs{i} is a

structure defining the network output from layer i.

Function Properties
net.adaptFcn Name of a network adaption function or ''

net.initFcn Name of a network initialization function or ''

net.performFcn Name of a network performance function or ''

net.trainFcn Name of a network training function or ''

Parameter Properties
net.adaptParam Network adaption parameters

net.initParam Network initialization parameters

net.performParam Network performance parameters

net.trainParam Network training parameters

http://www.mathworks.com/help/deeplearning/ref/network.html;jsessionid=0e8ce9952d7915d2fe746ae2fa54 2/4
10/29/2018 Create custom neural network - MATLAB network

Weight and Bias Value Properties

net.IW numLayers-by-numInputs cell array of input weight values

net.LW numLayers-by-numLayers cell array of layer weight values

net.b numLayers-by-1 cell array of bias values

Other Properties
net.userdata Structure you can use to store useful values

Examples

Create Network with One Input and Two Layers

This example shows how to create a network without any inputs and layers, and then set its numbers of inputs and layers
to 1 and 2 respectively.

net = network
net.numInputs = 1
net.numLayers = 2

Alternatively, you can create the same network with one line of code.

net = network(1,2)

Create Feedforward Network and View Properties

This example shows how to create a one-input, two-layer, feedforward network. Only the first layer has a bias. An input
weight connects to layer 1 from input 1. A layer weight connects to layer 2 from layer 1. Layer 2 is a network output and has
a target.

net = network(1,2,[1;0],[1; 0],[0 0; 1 0],[0 1])

You can view the network subobjects with the following code.

net.inputs{1}
net.layers{1}, net.layers{2}
net.biases{1}
net.inputWeights{1,1}, net.layerWeights{2,1}
net.outputs{2}

You can alter the properties of any of the network subobjects. This code changes the transfer functions of both layers:

net.layers{1}.transferFcn = 'tansig';
net.layers{2}.transferFcn = 'logsig';

You can view the weights for the connection from the first input to the first layer as follows. The weights for a connection
from an input to a layer are stored in net.IW. If the values are not yet set, these result is empty.

net.IW{1,1}

You can view the weights for the connection from the first layer to the second layer as follows. Weights for a connection
from a layer to a layer are stored in net.LW. Again, if the values are not yet set, the result is empty.

net.LW{2,1}

You can view the bias values for the first layer as follows.
http://www.mathworks.com/help/deeplearning/ref/network.html;jsessionid=0e8ce9952d7915d2fe746ae2fa54 3/4
10/29/2018 Create custom neural network - MATLAB network

net.b{1}

To change the number of elements in input 1 to 2, set each element’s range:

net.inputs{1}.range = [0 1; -1 1];

To simulate the network for a two-element input vector, the code might look like this:

p = [0.5; -0.1];
y = sim(net,p)

See Also
sim

Topics
Neural Network Object Properties
Neural Network Subobject Properties

Introduced before R2006a

How useful was this information?

http://www.mathworks.com/help/deeplearning/ref/network.html;jsessionid=0e8ce9952d7915d2fe746ae2fa54 4/4