(8.11) | |||
(8.12) | |||
(8.13) | |||
(8.14) | |||
(8.15) |
The weight vector at is the result of the summation of the weight vector at and the product of the learning constant with the activation value of the evolving neuron and the error vector . The calculated output vector contains all the output activations . The output activation is in the cited papers of Watts and Kasabov not clearly defined. We are using here a sigmoid function which takes as exponent the sum of the product of the weight vector of all weights connected to an output neuron from connected evolving neurons, where each sending neuron has the activity . Additionally one has to use some threshold if the gvalues of are all binary.
A more detailed description of the SECoS as well as discussion of its properties can be found in the application examples below.
Gerd Doeben-Henisch 2012-03-31