Documentation

network

Create custom shallow 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 vector If net.biasConnect(i) is 1, then layer i has a bias, and net.biases{i} is a structure describing that bias. net.inputConnect numLayer-by-numInputs Boolean vector If net.inputConnect(i,j) is 1, then layer i has a weight coming from input j, and net.inputWeights{i,j} is a structure describing that weight. net.layerConnect numLayer-by-numLayers Boolean vector If net.layerConnect(i,j) is 1, then layer i has a weight coming from layer j, and net.layerWeights{i,j} is a structure describing that weight. net.outputConnect 1-by-numLayers Boolean vector If net.outputConnect(i) is 1, then the network has an output from layer i, and net.outputs{i} is a structure describing that output. net.numOutputs 0 or a positive integer (read only) Number of network outputs according to net.outputConnect. net.numInputDelays 0 or a positive integer (read only) Maximum input delay according to all net.inputWeights{i,j}.delays. net.numLayerDelays 0 or a positive number (read only) Maximum layer delay according to all 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 cell array If net.inputConnect(i,j) is 1, then net.inputWeights{i,j} is a structure defining the weight to layer i from input j. net.layerWeights numLayers-by-numLayers cell array If net.layerConnect(i,j) is 1, then 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

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.

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)