| Neural Network Toolbox | Search Help Desk |
| dsse | Examples See Also |
Sum squared error performance derivative function
dPerf_dE = dsse('e',E,X,perf,PP)
dPerf_dX = dsse('x',E,X,perf,PP)
dsse is the derivative function for sse.
dsse('d',E,X,perf,PP) takes these arguments,
E - Matrix or cell array of error vector(s).
X - Vector of all weight and bias values.
perf - Network performance (ignored).
PP - Performance parameters (ignored).
dsse('x',E,X,perf,PP)returns the derivative dPerf_dX.
Here we define an error E and X for a network with one 3-element output and six weight and bias values.
E = {[1; -2; 0.5]};
X = [0; 0.2; -2.2; 4.1; 0.1; -0.2];
Here we calculate the network's sum squared error performance, and derivatives of performance.
perf = sse(E)
dPerf_dE = dsse('e',E,X)
dPerf_dX = dsse('x',E,X)
Note that sse can be called with only one argument and dsse with only three arguments because the other arguments are ignored. The other arguments exist so that sse and dsse conform to standard performance function argument lists.
sse