MATLAB: Neural net visualisation

neural network

I'm able to produce neural nets that work but I want to know what the resulting network looks like. Ideally some sort of graph with edges for each neuron showing their weights. If this does not exist, could someone give me a description of the network object output that will let me find and understand the weights myself?

Best Answer

The simplest solutions use integer weights, two hidden nodes with sign activation functions, purelin output activation functions and polar binary targets [-1 1 1 -1].

Since there are only 4 training equations for estimating (2+1)*2+(2+1)*1 = 9 weights, solutions are far from being unique without other constraints.

You can play around with the equations and determine your own version of "simplest solutions".

These can be easily transformed into solutions for continuous activation functions by replacing sign with tansig. The transformation of purelin to tansig or logsig is also straightforward.

Good Luck.

Greg

Related Solutions

MATLAB: Normalize Inputs and Targets of neural network

MAPMINMAX can be inappropriate only if there are outliers.

Use MAPSTD to detect outliers that can be removed or modified.

Hope this helps.

Thank you for formally accepting my answer

Greg

MATLAB: How to use weights and bias from Neural Network Toolbox for classification

I found the answer (output and yy are equal):

% Simulated a Neural Network
clear
close
clc
rng default
[x,y] = simpleclass_dataset;
neurons = 10;
net = feedforwardnet(neurons);
net = train(net,x,y);
outputs = sim(net,x);
% outputs = round(outputs);
figure, plotconfusion(y,outputs)
w1 = net.IW{1,1};
w2 = net.LW{2,1};
b1 = net.b{1};
b2 = net.b{2};
xx = x;
for ii = 1:length(net.inputs{1}.processFcns)
    xx = feval(net.inputs{1}.processFcns{ii},...
        'apply',xx,net.inputs{1}.processSettings{ii});
end
a1 = tanh(w1*xx + b1);
yy = purelin(w2*a1 + b2);
for mm = 1:length(net.outputs{1,2}.processFcns)
    yy = feval(net.outputs{1,2}.processFcns{mm},...
        'reverse',yy,net.outputs{1,2}.processSettings{mm});
end
figure, plotconfusion(y,yy)

Best Answer

Related Solutions

MATLAB: Normalize Inputs and Targets of neural network

MATLAB: How to use weights and bias from Neural Network Toolbox for classification

Related Question