This is demonstration of a two-layer neural network used to fit a function. You can use the sliders on the right to interactively see how individual parameters affect the output.
t(x) = 0.3 + 0.4*x + 0.5*sin(2.7*x) + 1.1/(1 + x^2)
y(x) = W_{2} tanh(W_{1} x + b_{1}) + b_{2}For example, for n=2 hidden units and 1 dimensional input and output, there are 7 parameters,
y(x) = w_{1,2} tanh(w_{1,1} x + b_{1,1}) + w_{2,2} tanh(w_{1,2} x + b_{1,2}) + b_{2}